To see the other types of publications on this topic, follow the link: Metric Learning Approaches.
Journal articles on the topic 'Metric Learning Approaches'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Metric Learning Approaches.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Sandiwarno, Sulis. "Empirical lecturers’ and students’ satisfaction assessment in e-learning systems based on the usage metrics." Research and Evaluation in Education 7, no. 2 (December 30, 2021): 118–31. http://dx.doi.org/10.21831/reid.v7i2.39642.
Full textAbstract:
Nowadays, in the pandemic of COVID-19, e-learning systems have been widely used to facilitate teaching and learning processes between lecturers and students. Assessing lecturers’ and students’ satisfaction with e-learning systems has become essential in improving the quality of education for higher learning institutions. Most existing approaches have attempted to assess users’ satisfaction based on System Usability Scale (SUS). On the other hand, different studies proposed usage-based metrics (completion rate, task duration, and mouse or cursor distance) which assess users’ satisfaction based on how they use and interact with the system. However, the cursor or mouse distance metric does not consider the effectiveness of navigation in e-learning systems, and such approaches measure either lecturers’ or students’ satisfaction independently. Towards this end, we propose a lostness metric to replace the click or cursor distance metric for assessing lecturers’ and students’ satisfaction with using e-learning systems. Furthermore, to obtain a deep analysis of users’ satisfaction, we tandem the usage-based metric (i.e., completion rate, task duration, and lostness) and the SUS metric. The evaluation results indicate that the proposed approach can precisely predict users’ satisfaction with e-learning systems.
2
Li, Zilong. "A Boosting-Based Deep Distance Metric Learning Method." Computational Intelligence and Neuroscience 2022 (March 15, 2022): 1–9. http://dx.doi.org/10.1155/2022/2665843.
Full textAbstract:
By leveraging neural networks, deep distance metric learning has yielded impressive results in computer vision applications. However, the existing approaches mostly focus a single deep distance metric based on pairs or triplets of samples. It is difficult for them to handle heterogeneous data and avoid overfitting. This study proposes a boosting-based learning method of multiple deep distance metrics, which generates the final distance metric through iterative training of multiple weak distance metrics. Firstly, the distance of sample pairs was mapped by a convolution neural network (CNN) and evaluated by a piecewise linear function. Secondly, the evaluation function was added as a weak learner to the boosting algorithm to generate a strong learner. Each weak learner targets the difficult samples different from the samples of previous learners. Next, an alternating optimization method was employed to train the network and loss function. Finally, the effectiveness of our method was demonstrated in contrast to state of the arts on retrieving the images from the CUB-200-2011, Cars-196, and Stanford Online Products (SOP) datasets.
3
Dutta, Ujjal Kr, Mehrtash Harandi, and C. Chandra Sekhar. "Unsupervised Metric Learning with Synthetic Examples." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (April 3, 2020): 3834–41. http://dx.doi.org/10.1609/aaai.v34i04.5795.
Full textAbstract:
Distance Metric Learning (DML) involves learning an embedding that brings similar examples closer while moving away dissimilar ones. Existing DML approaches make use of class labels to generate constraints for metric learning. In this paper, we address the less-studied problem of learning a metric in an unsupervised manner. We do not make use of class labels, but use unlabeled data to generate adversarial, synthetic constraints for learning a metric inducing embedding. Being a measure of uncertainty, we minimize the entropy of a conditional probability to learn the metric. Our stochastic formulation scales well to large datasets, and performs competitive to existing metric learning methods.
4
Yang, Lu, Peng Wang, and Yanning Zhang. "Stop-Gradient Softmax Loss for Deep Metric Learning." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 3 (June 26, 2023): 3164–72. http://dx.doi.org/10.1609/aaai.v37i3.25421.
Full textAbstract:
Deep metric learning aims to learn a feature space that models the similarity between images, and feature normalization is a critical step for boosting performance. However directly optimizing L2-normalized softmax loss cause the network to fail to converge. Therefore some SOTA approaches appends a scale layer after the inner product to relieve the convergence problem, but it incurs a new problem that it's difficult to learn the best scaling parameters. In this letter, we look into the characteristic of softmax-based approaches and propose a novel learning objective function Stop-Gradient Softmax Loss (SGSL) to solve the convergence problem in softmax-based deep metric learning with L2-normalization. In addition, we found a useful trick named Remove the last BN-ReLU (RBR). It removes the last BN-ReLU in the backbone to reduce the learning burden of the model. Experimental results on four fine-grained image retrieval benchmarks show that our proposed approach outperforms most existing approaches, i.e., our approach achieves 75.9% on CUB-200-2011, 94.7% on CARS196 and 83.1% on SOP which outperforms other approaches at least 1.7%, 2.9% and 1.7% on Recall@1.
5
Dutta, Ujjal Kr, Mehrtash Harandi, and C. Chandra Shekhar. "Semi-Supervised Metric Learning: A Deep Resurrection." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 8 (May 18, 2021): 7279–87. http://dx.doi.org/10.1609/aaai.v35i8.16894.
Full textAbstract:
Distance Metric Learning (DML) seeks to learn a discriminative embedding where similar examples are closer, and dissimilar examples are apart. In this paper, we address the problem of Semi-Supervised DML (SSDML) that tries to learn a metric using a few labeled examples, and abundantly available unlabeled examples. SSDML is important because it is infeasible to manually annotate all the examples present in a large dataset. Surprisingly, with the exception of a few classical approaches that learn a linear Mahalanobis metric, SSDML has not been studied in the recent years, and lacks approaches in the deep SSDML scenario. In this paper, we address this challenging problem, and revamp SSDML with respect to deep learning. In particular, we propose a stochastic, graph-based approach that first propagates the affinities between the pairs of examples from labeled data, to that of the unlabeled pairs. The propagated affinities are used to mine triplet based constraints for metric learning. We impose orthogonality constraint on the metric parameters, as it leads to a better performance by avoiding a model collapse.
6
Kaya and Bilge. "Deep Metric Learning: A Survey." Symmetry 11, no. 9 (August 21, 2019): 1066. http://dx.doi.org/10.3390/sym11091066.
Full textAbstract:
Metric learning aims to measure the similarity among samples while using an optimal distance metric for learning tasks. Metric learning methods, which generally use a linear projection, are limited in solving real-world problems demonstrating non-linear characteristics. Kernel approaches are utilized in metric learning to address this problem. In recent years, deep metric learning, which provides a better solution for nonlinear data through activation functions, has attracted researchers' attention in many different areas. This article aims to reveal the importance of deep metric learning and the problems dealt with in this field in the light of recent studies. As far as the research conducted in this field are concerned, most existing studies that are inspired by Siamese and Triplet networks are commonly used to correlate among samples while using shared weights in deep metric learning. The success of these networks is based on their capacity to understand the similarity relationship among samples. Moreover, sampling strategy, appropriate distance metric, and the structure of the network are the challenging factors for researchers to improve the performance of the network model. This article is considered to be important, as it is the first comprehensive study in which these factors are systematically analyzed and evaluated as a whole and supported by comparing the quantitative results of the methods.
7
Syed, Muhamamd Adnan, Zhenjun Han, Zhaoju Li, and Jianbin Jiao. "Impostor Resilient Multimodal Metric Learning for Person Reidentification." Advances in Multimedia 2018 (2018): 1–11. http://dx.doi.org/10.1155/2018/3202495.
Full textAbstract:
In person reidentification distance metric learning suffers a great challenge from impostor persons. Mostly, distance metrics are learned by maximizing the similarity between positive pair against impostors that lie on different transform modals. In addition, these impostors are obtained from Gallery view for query sample only, while the Gallery sample is totally ignored. In real world, a given pair of query and Gallery experience different changes in pose, viewpoint, and lighting. Thus, impostors only from Gallery view can not optimally maximize their similarity. Therefore, to resolve these issues we have proposed an impostor resilient multimodal metric (IRM3). IRM3 is learned for each modal transform in the image space and uses impostors from both Probe and Gallery views to effectively restrict large number of impostors. Learned IRM3 is then evaluated on three benchmark datasets, VIPeR, CUHK01, and CUHK03, and shows significant improvement in performance compared to many previous approaches.
8
Saha, Soumadeep, Utpal Garain, Arijit Ukil, Arpan Pal, and Sundeep Khandelwal. "MedTric : A clinically applicable metric for evaluation of multi-label computational diagnostic systems." PLOS ONE 18, no. 8 (August 10, 2023): e0283895. http://dx.doi.org/10.1371/journal.pone.0283895.
Full textAbstract:
When judging the quality of a computational system for a pathological screening task, several factors seem to be important, like sensitivity, specificity, accuracy, etc. With machine learning based approaches showing promise in the multi-label paradigm, they are being widely adopted to diagnostics and digital therapeutics. Metrics are usually borrowed from machine learning literature, and the current consensus is to report results on a diverse set of metrics. It is infeasible to compare efficacy of computational systems which have been evaluated on different sets of metrics. From a diagnostic utility standpoint, the current metrics themselves are far from perfect, often biased by prevalence of negative samples or other statistical factors and importantly, they are designed to evaluate general purpose machine learning tasks. In this paper we outline the various parameters that are important in constructing a clinical metric aligned with diagnostic practice, and demonstrate their incompatibility with existing metrics. We propose a new metric, MedTric that takes into account several factors that are of clinical importance. MedTric is built from the ground up keeping in mind the unique context of computational diagnostics and the principle of risk minimization, penalizing missed diagnosis more harshly than over-diagnosis. MedTric is a unified metric for medical or pathological screening system evaluation. We compare this metric against other widely used metrics and demonstrate how our system outperforms them in key areas of medical relevance.
9
Bhukar, Karan, Harshit Kumar, Dinesh Raghu, and Ajay Gupta. "End-to-End Deep Reinforcement Learning for Conversation Disentanglement." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 11 (June 26, 2023): 12571–79. http://dx.doi.org/10.1609/aaai.v37i11.26480.
Full textAbstract:
Collaborative Communication platforms (e.g., Slack) support multi-party conversations which contain a large number of messages on shared channels. Multiple conversations intermingle within these messages. The task of conversation disentanglement is to cluster these intermingled messages into conversations. Existing approaches are trained using loss functions that optimize only local decisions, i.e. predicting reply-to links for each message and thereby creating clusters of conversations. In this work, we propose an end-to-end reinforcement learning (RL) approach that directly optimizes a global metric. We observe that using existing global metrics such as variation of information and adjusted rand index as a reward for the RL agent deteriorates its performance. This behaviour is because these metrics completely ignore the reply-to links between messages (local decisions) during reward computation. Therefore, we propose a novel thread-level reward function that captures the global metric without ignoring the local decisions. Through experiments on the Ubuntu IRC dataset, we demonstrate that the proposed RL model improves the performance on both link-level and conversation-level metrics.
10
Komamizu, Takahiro. "Combining Multi-ratio Undersampling and Metric Learning for Imbalanced Classification." Journal of Data Intelligence 2, no. 4 (December 2021): 462–75. http://dx.doi.org/10.26421/jdi2.4-5.
Full textAbstract:
In classification, class imbalance is a factor that degrades the classification performance of many classification methods. Resampling is one widely accepted approach to the class imbalance; however, it still suffers from an insufficient data space, which also degrades performance. To overcome this, in this paper, an undersampling-based imbalanced classification framework, MMEnsemble, is proposed that incorporates metric learning into a multi-ratio undersampling-based ensemble. This framework also overcomes a problem with determining the appropriate sampling ratio in the multi-ratio ensemble method. It was evaluated by using 12 real-world datasets. It outperformed the state-of-the-art approaches of metric learning, undersampling, and oversampling in recall and ROC-AUC, and it performed comparably with them in terms of Gmean and F-measure metrics.
11
Srinivasan, Sriram, Golnoosh Farnadi, and Lise Getoor. "BOWL: Bayesian Optimization for Weight Learning in Probabilistic Soft Logic." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 06 (April 3, 2020): 10267–75. http://dx.doi.org/10.1609/aaai.v34i06.6589.
Full textAbstract:
Probabilistic soft logic (PSL) is a statistical relational learning framework that represents complex relational models with weighted first-order logical rules. The weights of the rules in PSL indicate their importance in the model and influence the effectiveness of the model on a given task. Existing weight learning approaches often attempt to learn a set of weights that maximizes some function of data likelihood. However, this does not always translate to optimal performance on a desired domain metric, such as accuracy or F1 score. In this paper, we introduce a new weight learning approach called Bayesian optimization for weight learning (BOWL) based on Gaussian process regression that directly optimizes weights on a chosen domain performance metric. The key to the success of our approach is a novel projection that captures the semantic distance between the possible weight configurations. Our experimental results show that our proposed approach outperforms likelihood-based approaches and yields up to a 10% improvement across a variety of performance metrics. Further, we performed experiments to measure the scalability and robustness of our approach on various realworld datasets.
12
Kertész, Gábor. "Deep Metric Learning Using Negative Sampling Probability Annealing." Sensors 22, no. 19 (October 6, 2022): 7579. http://dx.doi.org/10.3390/s22197579.
Full textAbstract:
Multiple studies have concluded that the selection of input samples is key for deep metric learning. For triplet networks, the selection of the anchor, positive, and negative pairs is referred to as triplet mining. The selection of the negatives is considered the be the most complicated task, due to a large number of possibilities. The goal is to select a negative that results in a positive triplet loss; however, there are multiple approaches for this—semi-hard negative mining or hardest mining are well-known in addition to random selection. Since its introduction, semi-hard mining was proven to outperform other negative mining techniques; however, in recent years, the selection of the so-called hardest negative has shown promising results in different experiments. This paper introduces a novel negative sampling solution based on dynamic policy switching, referred to as negative sampling probability annealing, which aims to exploit the positives of all approaches. Results are validated on an experimental synthetic dataset using cluster-analysis methods; finally, the discriminative abilities of trained models are measured on real-life data.
13
Liu, Wei, Xinmei Tian, Dacheng Tao, and Jianzhuang Liu. "Constrained Metric Learning Via Distance Gap Maximization." Proceedings of the AAAI Conference on Artificial Intelligence 24, no. 1 (July 3, 2010): 518–24. http://dx.doi.org/10.1609/aaai.v24i1.7701.
Full textAbstract:
Vectored data frequently occur in a variety of fields, which are easy to handle since they can be mathematically abstracted as points residing in a Euclidean space. An appropriate distance metric in the data space is quite demanding for a great number of applications. In this paper, we pose robust and tractable metric learning under pairwise constraints that are expressed as similarity judgements between data pairs. The major features of our approach include: 1) it maximizes the gap between the average squared distance among dissimilar pairs and the average squared distance among similar pairs; 2) it is capable of propagating similar constraints to all data pairs; and 3) it is easy to implement in contrast to the existing approaches using expensive optimization such as semidefinite programming. Our constrained metric learning approach has widespread applicability without being limited to particular backgrounds. Quantitative experiments are performed for classification and retrieval tasks, uncovering the effectiveness of the proposed approach.
14
Gomoluch, Paweł, Dalal Alrajeh, and Alessandra Russo. "Learning Classical Planning Strategies with Policy Gradient." Proceedings of the International Conference on Automated Planning and Scheduling 29 (May 25, 2021): 637–45. http://dx.doi.org/10.1609/icaps.v29i1.3531.
Full textAbstract:
A common paradigm in classical planning is heuristic forward search. Forward search planners often rely on simple best-first search which remains fixed throughout the search process. In this paper, we introduce a novel search framework capable of alternating between several forward search approaches while solving a particular planning problem. Selection of the approach is performed using a trainable stochastic policy, mapping the state of the search to a probability distribution over the approaches. This enables using policy gradient to learn search strategies tailored to a specific distributions of planning problems and a selected performance metric, e.g. the IPC score. We instantiate the framework by constructing a policy space consisting of five search approaches and a two-dimensional representation of the planner’s state. Then, we train the system on randomly generated problems from five IPC domains using three different performance metrics. Our experimental results show that the learner is able to discover domain-specific search strategies, improving the planner’s performance relative to the baselines of plain bestfirst search and a uniform policy.
15
Qiu, Wei. "Based on Semi-Supervised Clustering with the Boost Similarity Metric Method for Face Retrieval." Applied Mechanics and Materials 543-547 (March 2014): 2720–23. http://dx.doi.org/10.4028/www.scientific.net/amm.543-547.2720.
Full textAbstract:
The focus of this paper is on Metric Learning, with particular interest in incorporating side information to make it semi-supervised. This study is primarily motivated by an application: face-image clustering. In the paper introduces metric learning and semi-supervised clustering, Boost the similarity metric learning method that adapt the underlying similarity metric used by the clustering algorithm. we propose a novel idea of learning with historical relevance feedback log data, and adopt a new paradigm called Boost the Similarity Metric Method for Face Retrieval, Experimental results demonstrate that the unified approach produces better clusters than both individual approaches as well as previously proposed semi-supervised clustering algorithms. This paper followed by the discussion of experiments on face-image clustering.
16
Shen, Yican. "Research on the Few-Shot Learning Based on Metrics." SHS Web of Conferences 144 (2022): 03008. http://dx.doi.org/10.1051/shsconf/202214403008.
Full textAbstract:
Deep learning has been rapidly developed and obtained great achievements with a dataintensive condition. However, sufficient datasets are not always available in practical application. In the absence of data, humans can still perform well in studying and recognizing new items while it becomes a hard task for the computer to learn and generate from a small dataset. Thus, researchers are increasingly interested in few-shot learning. The purpose of few-shot learning is to allow computers to carry out unknown tasks with a few examples. Recently, effective few-shot models have frequently been designed using transfer learning approaches, with the metric method being an important branch in transfer learning. This article reviews the metric methodologies for few-short learning, analyzing the development of the metric based few-shot learning in the following three categories: traditional metric methods, relation network based metric methods and graph based metric methods. Then it compares the effectiveness of those models on a representative dataset and illustrates the feature of each category. Finally, it discusses the potential future research fields.
17
Fu, Zheren, Yan Li, Zhendong Mao, Quan Wang, and Yongdong Zhang. "Deep Metric Learning with Self-Supervised Ranking." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 2 (May 18, 2021): 1370–78. http://dx.doi.org/10.1609/aaai.v35i2.16226.
Full textAbstract:
Deep metric learning aims to learn a deep embedding space, where similar objects are pushed towards together and different objects are repelled against. Existing approaches typically use inter-class characteristics, e.g. class-level information or instance-level similarity, to obtain semantic relevance of data points and get a large margin between different classes in the embedding space. However, the intra-class characteristics, e.g. local manifold structure or relative relationship within the same class, are usually overlooked in the learning process. Hence the data structure cannot be fully exploited and the output embeddings have limitation in retrieval. More importantly, retrieval results lack in a good ranking. This paper presents a novel self-supervised ranking auxiliary framework, which captures intra-class characteristics as well as inter-class characteristics for better metric learning. Our method defines specific transform functions to simulates the local structure change of intra-class in the initial image domain, and formulates a self-supervised learning procedure to fully exploit this property and preserve it in the embedding space. Extensive experiments on three standard benchmarks show that our method significantly improves and outperforms the state-of-the-art methods on the performances of both retrieval and ranking by 2%-4%.
18
Kim, Jonathan, and Stefan Bekiranov. "Generalization Performance of Quantum Metric Learning Classifiers." Biomolecules 12, no. 11 (October 27, 2022): 1576. http://dx.doi.org/10.3390/biom12111576.
Full textAbstract:
Quantum computing holds great promise for a number of fields including biology and medicine. A major application in which quantum computers could yield advantage is machine learning, especially kernel-based approaches. A recent method termed quantum metric learning, in which a quantum embedding which maximally separates data into classes is learned, was able to perfectly separate ant and bee image training data. The separation is achieved with an intrinsically quantum objective function and the overall approach was shown to work naturally as a hybrid classical-quantum computation enabling embedding of high dimensional feature data into a small number of qubits. However, the ability of the trained classifier to predict test sample data was never assessed. We assessed the performance of quantum metric learning on test ants and bees image data as well as breast cancer clinical data. We applied the original approach as well as variants in which we performed principal component analysis (PCA) on the feature data to reduce its dimensionality for quantum embedding, thereby limiting the number of model parameters. If the degree of dimensionality reduction was limited and the number of model parameters was constrained to be far less than the number of training samples, we found that quantum metric learning was able to accurately classify test data.
19
Yang, Wei, Luhui Xu, Xiaopan Chen, Fengbin Zheng, and Yang Liu. "Chi-Squared Distance Metric Learning for Histogram Data." Mathematical Problems in Engineering 2015 (2015): 1–12. http://dx.doi.org/10.1155/2015/352849.
Full textAbstract:
Learning a proper distance metric for histogram data plays a crucial role in many computer vision tasks. The chi-squared distance is a nonlinear metric and is widely used to compare histograms. In this paper, we show how to learn a general form of chi-squared distance based on the nearest neighbor model. In our method, the margin of sample is first defined with respect to the nearest hits (nearest neighbors from the same class) and the nearest misses (nearest neighbors from the different classes), and then the simplex-preserving linear transformation is trained by maximizing the margin while minimizing the distance between each sample and its nearest hits. With the iterative projected gradient method for optimization, we naturally introduce thel2,1norm regularization into the proposed method for sparse metric learning. Comparative studies with the state-of-the-art approaches on five real-world datasets verify the effectiveness of the proposed method.
20
Kim, Yonghyun, and Wonpyo Park. "Multi-level Distance Regularization for Deep Metric Learning." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 3 (May 18, 2021): 1827–35. http://dx.doi.org/10.1609/aaai.v35i3.16277.
Full textAbstract:
We propose a novel distance-based regularization method for deep metric learning called Multi-level Distance Regularization (MDR). MDR explicitly disturbs a learning procedure by regularizing pairwise distances between embedding vectors into multiple levels that represents a degree of similarity between a pair. In the training stage, the model is trained with both MDR and an existing loss function of deep metric learning, simultaneously; the two losses interfere with the objective of each other, and it makes the learning process difficult. Moreover, MDR prevents some examples from being ignored or overly influenced in the learning process. These allow the parameters of the embedding network to be settle on a local optima with better generalization. Without bells and whistles, MDR with simple Triplet loss achieves the-state-of-the-art performance in various benchmark datasets: CUB-200-2011, Cars-196, Stanford Online Products, and In-Shop Clothes Retrieval. We extensively perform ablation studies on its behaviors to show the effectiveness of MDR. By easily adopting our MDR, the previous approaches can be improved in performance and generalization ability.
21
Gräßer, Felix, Hagen Malberg, and Sebastian Zaunseder. "Neighborhood Optimization for Therapy Decision Support." Current Directions in Biomedical Engineering 5, no. 1 (September 1, 2019): 1–4. http://dx.doi.org/10.1515/cdbme-2019-0001.
Full textAbstract:
AbstractThis work targets the development of a neighborhood-based Collaborative Filtering therapy recommender system for clinical decision support. The proposed algorithm estimates outcome of pharmaceutical therapy options in order to derive recommendations. Two approaches, namely a Relief-based algorithm and a metric learning approach are investigated. Both adapt similarity functions to the underlying data in order to determine the neighborhood incorporated into the filtering process. The implemented approaches are evaluated regarding the accuracy of the outcome estimations. The metric learning approach can outperform the Relief-based algorithms. It is, however, inferior regarding explainability of the generated recommendations.
22
Chen, Baifan, Meng Peng, Lijue Liu, and Tao Lu. "Visual Tracking with Multilevel Sparse Representation and Metric Learning." Journal of Information Technology Research 11, no. 2 (April 2018): 1–12. http://dx.doi.org/10.4018/jitr.2018040101.
Full textAbstract:
Visual tracking arises in various real-world tasks where an object should be located in a video. Sparse representation can implement tracking problems by linearly representing object with a few templates. However, this approach has two main shortcomings. Namely, setting the templates updating frequency is difficult and meanwhile it is relatively weak in distinguishing the object from the background. For solving these problems, the author models a multilevel object template set that can be stratified by different updating time spans. The hierarchical structure and updating strategy promise the real-timeness, stability, and diversity of object template. Additionally, metric learning is combined to evaluate the object candidates and thereby improve the discriminative ability. Experiments on well-known visual tracking datasets demonstrate that the proposed method can track an object more robustly and accurately compared to the state-of-the-art approaches.
23
Jabbar, Ayad Mohammed, and Ku Ruhana Ku-Mahamud. "Grey wolf optimization algorithm for hierarchical document clustering." Indonesian Journal of Electrical Engineering and Computer Science 24, no. 3 (December 1, 2021): 1744. http://dx.doi.org/10.11591/ijeecs.v24.i3.pp1744-1758.
Full textAbstract:
In data mining, the application of grey wolf optimization (GWO) algorithm has been used in several learning approaches because of its simplicity in adapting to different application domains. Most recent works that concern unsupervised learning have focused on text clustering, where the GWO algorithm shows promising results. Although GWO has great potential in performing text clustering, it has limitations in dealing with outlier documents and noise data. This research introduces medoid GWO (M-GWO) algorithm, which incorporates a medoid recalculation process to share the information of medoids among the three best wolves and the rest of the population. This improvement aims to find the best set of medoids during the algorithm run and increases the exploitation search to find more local regions in the search space. Experimental results obtained from using well-known algorithms, such as genetic, firefly, GWO, and k-means algorithms, in four benchmarks. The results of external evaluation metrics, such as rand, purity, F-measure, and entropy, indicates that the proposed M-GWO algorithm achieves better document clustering than all other algorithms (i.e., 75% better when using Rand metric, 50% better than all algorithm based on purity metric, 75% better than all algorithms using F-measure metric, and 100% based on entropy metric).
24
Lavanya, L., Chebrolu Ujwala Pavani, Gadchanda Vineeth, and Borada Lavanya. "Operational Multi-Modal Distance Metric Learning to Image Reclamation." International Journal of Engineering & Technology 7, no. 2.32 (May 31, 2018): 405. http://dx.doi.org/10.14419/ijet.v7i2.32.15725.
Full textAbstract:
Distance learning is an eminent technique that improves the search for images based on content. Although widely studied, most DML approaches generally recognize a modalization training framework that teaches a metric distance or a combination of distances in which several types of characteristics are simply interconnected. DML methods of that type suffer some critical limitations (a) Some feature types can significantly overwhelm others with the DML assignment, due to different attributes, and (b) the distance learning standard in the combined metric properties can be consumed using the feature attribute approach combined. In this article we refer to these the restrictions are reviewed online- multimodal distance metric training scheme (OMDML), which explores a dual duplication online learning scheme. (c) learn to optimize the distance metric in each owner space separately; and (d) learn find the optimal combination of different types of characteristics. To overestimate the cost of DML in sophisticated areas, we offer a low level OMDML algorithm that not only reduces estimated costs, but also guarantees high accuracy. We are here carried out exhaustive experiments to estimate the performance of the algorithms proposed for the restoration of multimedia images.
25
Zhao, Wenda, Ruikai Yang, Yu Liu, and You He. "Style-Content Metric Learning for Multidomain Remote Sensing Object Recognition." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 3 (June 26, 2023): 3624–32. http://dx.doi.org/10.1609/aaai.v37i3.25473.
Full textAbstract:
Previous remote sensing recognition approaches predominantly perform well on the training-testing dataset. However, due to large style discrepancies not only among multidomain datasets but also within a single domain, they suffer from obvious performance degradation when applied to unseen domains. In this paper, we propose a style-content metric learning framework to address the generalizable remote sensing object recognition issue. Specifically, we firstly design an inter-class dispersion metric to encourage the model to make decision based on content rather than the style, which is achieved by dispersing predictions generated from the contents of both positive sample and negative sample and the style of input image. Secondly, we propose an intra-class compactness metric to force the model to be less style-biased by compacting classifier's predictions from the content of input image and the styles of positive sample and negative sample. Lastly, we design an intra-class interaction metric to improve model's recognition accuracy by pulling in classifier's predictions obtained from the input image and positive sample. Extensive experiments on four datasets show that our style-content metric learning achieves superior generalization performance against the state-of-the-art competitors. Code and model are available at: https://github.com/wdzhao123/TSCM.
26
Shen, Fangyao, Yong Peng, Guojun Dai, Baoliang Lu, and Wanzeng Kong. "Coupled Projection Transfer Metric Learning for Cross-Session Emotion Recognition from EEG." Systems 10, no. 2 (April 11, 2022): 47. http://dx.doi.org/10.3390/systems10020047.
Full textAbstract:
Distribution discrepancies between different sessions greatly degenerate the performance of video-evoked electroencephalogram (EEG) emotion recognition. There are discrepancies since the EEG signal is weak and non-stationary and these discrepancies are manifested in different trails in each session and even in some trails which belong to the same emotion. To this end, we propose a Coupled Projection Transfer Metric Learning (CPTML) model to jointly complete domain alignment and graph-based metric learning, which is a unified framework to simultaneously minimize cross-session and cross-trial divergences. By experimenting on the SEED_IV emotional dataset, we show that (1) CPTML exhibits a significantly better performance than several other approaches; (2) the cross-session distribution discrepancies are minimized and emotion metric graph across different trials are optimized in the CPTML-induced subspace, indicating the effectiveness of data alignment and metric exploration; and (3) critical EEG frequency bands and channels for emotion recognition are automatically identified from the learned projection matrices, providing more insights into the occurrence of the effect.
27
Kahraman, H. Tolga, Seref Sagiroglu, and Ilhami Colak. "Novel User Modeling Approaches for Personalized Learning Environments." International Journal of Information Technology & Decision Making 15, no. 03 (May 2016): 575–602. http://dx.doi.org/10.1142/s0219622016500164.
Full textAbstract:
Modeling user knowledge and creating user profiles not only for special web-based social media but also for complex and mixed personalized learning environments are important research challenges. The key component for adaptation is the user’s knowledge model. This paper introduces fuzzy metric (FM)-based novel and efficient similarity measurement method and adaptive artificial neural network (AANN) and artificial bee colony (ABC)-based knowledge classification approaches for personalized learning environments. For this purpose, FM-based method has been developed to measure distances more efficiently among the users and their knowledge model using the web logs/session data. In addition, a novel knowledge classifier based on ABC and AANN having combined with the generic object model has been developed for user modeling strategies and user modeling server of adaptive educational electric course (AEEC). Finally, the approaches have been tested to compare the classification performance of the user modeling methods developed for user modeling task. The experimental results have shown that proposed methods have improved similarity measurements considerably and decreased the misclassifications in user modeling processes. Thus, powerful user modeling approaches have been presented to the literature. It is expected that the approaches introduced in this article can be a reference to others researches and to develop more adaptive and personalized web applications in future.
28
Madono, Koki, Masayuki Tanaka, Masaki Onishi, and Tetsuji Ogawa. "Scrambling Parameter Generation to Improve Perceptual Information Hiding." Electronic Imaging 2021, no. 11 (January 18, 2021): 155–1. http://dx.doi.org/10.2352/issn.2470-1173.2021.11.hvei-155.
Full textAbstract:
The present study proposes the method to improve the perceptual information hiding in image scramble approaches. Image scramble approaches have been used to overcome the privacy issues on the cloud-based machine learning approach. The performance of image scramble approaches are depending on the scramble parameters; because it decides the performance of perceptual information hiding. However, in existing image scramble approaches, the performance by scrambling parameters has not been quantitatively evaluated. This may be led to show private information in public. To overcome this issue, a suitable metric is investigated to hide PIH, and then scrambling parameter generation is proposed to combine image scramble approaches. Experimental comparisons using several image quality assessment metrics show that Learned Perceptual Image Patch Similarity (LPIPS) is suitable for PIH. Also, the proposed scrambling parameter generation is experimentally confirmed effective to hide PIH while keeping the classification performance.
29
Kim, Taehan, and Wonzoo Chung. "Collaborative Social Metric Learning in Trust Network for Recommender Systems." International Journal on Semantic Web and Information Systems 19, no. 1 (January 20, 2023): 1–15. http://dx.doi.org/10.4018/ijswis.316535.
Full textAbstract:
In this study, a novel top-K ranking recommendation method called collaborative social metric learning (CSML) is proposed, which implements a trust network that provides both user-item and user-user interactions in simple structure. Most existing recommender systems adopting trust networks focus on item ratings, but this does not always guarantee optimal top-K ranking prediction. Conventional direct ranking systems in trust networks are based on sub-optimal correlation approaches that do not consider item-item relations. The proposed CSML algorithm utilizes the metric learning method to directly predict the top-K items in a trust network. A new triplet loss is further proposed, called socio-centric loss, which represents user-user interactions to fully exploit the information contained in a trust network, as an addition to the two commonly used triplet losses in metric learning for recommender systems, which consider user-item and item-item relations. Experimental results demonstrate that the proposed CSML outperformed existing recommender systems for real-world trust network data.
30
Rudolph, George, and Tony Martinez. "Finding the Real Differences Between Learning Algorithms." International Journal on Artificial Intelligence Tools 24, no. 03 (June 2015): 1550001. http://dx.doi.org/10.1142/s0218213015500013.
Full textAbstract:
In the process of selecting a machine learning algorithm to solve a problem, questions like the following commonly arise: (1) Are some algorithms basically the same, or are they fundamentally different? (2) How different? (3) How do we measure that difference? (4) If we want to combine algorithms, what algorithms and combinators should be tried? This research proposes COD (Classifier Output Difference) distance as a diversity metric. COD separates difference from accuracy, COD goes beyond accuracy to consider differences in output behavior as the basis for comparison. The paper extends earlier on COD by giving a basic comparison to other diversity metrics, and by giving an example of using COD data as a predictive model from which to select algorithms to include in an ensemble. COD may fill a niche in metalearning as a predictive aid to selecting algorithms for ensembles and hybrid systems by providing a simple, straightforward, computationally reasonable alternative to other approaches.
31
Hu, Yuan, Lei Chen, Zhibin Wang, Xiang Pan, and Hao Li. "Towards a More Realistic and Detailed Deep-Learning-Based Radar Echo Extrapolation Method." Remote Sensing 14, no. 1 (December 22, 2021): 24. http://dx.doi.org/10.3390/rs14010024.
Full textAbstract:
Deep-learning-based radar echo extrapolation methods have achieved remarkable progress in the precipitation nowcasting field. However, they suffer from a common notorious problem—they tend to produce blurry predictions. Although some efforts have been made in recent years, the blurring problem is still under-addressed. In this work, we propose three effective strategies to assist deep-learning-based radar echo extrapolation methods to achieve more realistic and detailed prediction. Specifically, we propose a spatial generative adversarial network (GAN) and a spectrum GAN to improve image fidelity. The spatial and spectrum GANs aim at penalizing the distribution discrepancy between generated and real images from the spatial domain and spectral domain, respectively. In addition, a masked style loss is devised to further enhance the details by transferring the detailed texture of ground truth radar sequences to extrapolated ones. We apply a foreground mask to prevent the background noise from transferring to the outputs. Moreover, we also design a new metric termed the power spectral density score (PSDS) to quantify the perceptual quality from a frequency perspective. The PSDS metric can be applied as a complement to other visual evaluation metrics (e.g., LPIPS) to achieve a comprehensive measurement of image sharpness. We test our approaches with both ConvLSTM baseline and U-Net baseline, and comprehensive ablation experiments on the SEVIR dataset show that the proposed approaches are able to produce much more realistic radar images than baselines. Most notably, our methods can be readily applied to any deep-learning-based spatiotemporal forecasting models to acquire more detailed results.
32
ZHU, SONGHAO, ZHIWEI LIANG, and XIAOYUAN JING. "VIDEO RETRIEVAL VIA LEARNING COLLABORATIVE SEMANTIC DISTANCE." International Journal of Pattern Recognition and Artificial Intelligence 25, no. 04 (June 2011): 475–90. http://dx.doi.org/10.1142/s0218001411008944.
Full textAbstract:
Graph-based semi-supervised learning approaches have been proven effective and efficient in solving the problem of the inefficiency of labeled data in many real-world application areas, such as video annotation. However, the pairwise similarity metric, a significant factor of existing approaches, has not been fully investigated. That is, these graph-based semi-supervised approaches estimate the pairwise similarity between samples mainly according to the spatial property of video data. On the other hand, temporal property, an essential characteristic of video data, is not embedded into the pairwise similarity measure. Accordingly, a novel framework for video annotation, called Joint Spatio-Temporal Correlation Learning (JSTCL), is proposed in this paper. This framework is characterized by simultaneously taking into account the spatial and temporal property of video data to achieve more accurate pairwise similarity values. We apply the proposed framework to video annotation and report superior performance compared to key existing approaches over the benchmark TRECVID data set.
33
Vizilter, Yu V., O. V. Vygolov, S. Yu Zheltov, and V. V. Kniaz. "METRIC APPROACH TO SEMANTIC-MORPHOLOGICAL IMAGE COMPARISON." Vestnik komp'iuternykh i informatsionnykh tekhnologii, no. 191 (May 2020): 3–12. http://dx.doi.org/10.14489/vkit.2020.05.pp.003-012.
Full textAbstract:
In this paper we propose and consider different metric approaches to image comparison based on Morpho-Semantic (MS) and Semantic-Morphological (SM) models. The first proposed class-based approach presumes the embedding of MS and SM models to the metric space with weighted Lp metrics. This approach is based on representation of SM models as mosaic vector functions composed of semantic-morphological class expression maps. The feature description of these maps provides a global feature description of SM models by SM vectors. The second proposed class-based approach is based on resource models, which include semantic-morphological class expression maps with area recourse values. This approach implements the embedding of these mosaic class expression maps with area recourse values to the metric space with Earth Mover’s Distance (EMD) based on resource transportation between these maps. Finally, we propose the object-based approach to metric embedding of SM models inspired by Geometrical Difference Distance (GDD), which performs the comparison of mosaic image shapes via weighted pairwise comparison of their region shapes. In this way we obtain the SM Difference Distance (SMDD) and its EMD-version (SMDD). The practical applicability of proposed SM-metrics is largely determined by the strategy of feature set forming and parameter estimation scheme. The SM-metrics parameter tuning for comparison of some visual scenes/objects could be performed both as MS-modeling (interpretation) of human subjective reasoning and as MS-modeling (interpretation) of deep learning results. In both cases, SM models and SM metrics fitting could allow: making partially transparent the human or DNN reasoning in scene comparison tasks; Comparing (grouping, clustering) different experts (algorithms) in terms of different parameters settings for SM-models; performing the personalized post-training of neural network models with taking into account the individual SM-settings of concrete users, operators or experts. This will combine the effectiveness of deep learning on huge training bases with partial transparency of reasoning and the possibility of directly taking into account the wishes of users in terms of SM-models, rather than by creating the artificial training bases via artificial augmentation.
34
Vizilter, Yu V., O. V. Vygolov, S. Yu Zheltov, and V. V. Kniaz. "METRIC APPROACH TO SEMANTIC-MORPHOLOGICAL IMAGE COMPARISON." Vestnik komp'iuternykh i informatsionnykh tekhnologii, no. 191 (May 2020): 3–12. http://dx.doi.org/10.14489/vkit.2020.05.pp.003-012.
Full textAbstract:
In this paper we propose and consider different metric approaches to image comparison based on Morpho-Semantic (MS) and Semantic-Morphological (SM) models. The first proposed class-based approach presumes the embedding of MS and SM models to the metric space with weighted Lp metrics. This approach is based on representation of SM models as mosaic vector functions composed of semantic-morphological class expression maps. The feature description of these maps provides a global feature description of SM models by SM vectors. The second proposed class-based approach is based on resource models, which include semantic-morphological class expression maps with area recourse values. This approach implements the embedding of these mosaic class expression maps with area recourse values to the metric space with Earth Mover’s Distance (EMD) based on resource transportation between these maps. Finally, we propose the object-based approach to metric embedding of SM models inspired by Geometrical Difference Distance (GDD), which performs the comparison of mosaic image shapes via weighted pairwise comparison of their region shapes. In this way we obtain the SM Difference Distance (SMDD) and its EMD-version (SMDD). The practical applicability of proposed SM-metrics is largely determined by the strategy of feature set forming and parameter estimation scheme. The SM-metrics parameter tuning for comparison of some visual scenes/objects could be performed both as MS-modeling (interpretation) of human subjective reasoning and as MS-modeling (interpretation) of deep learning results. In both cases, SM models and SM metrics fitting could allow: making partially transparent the human or DNN reasoning in scene comparison tasks; Comparing (grouping, clustering) different experts (algorithms) in terms of different parameters settings for SM-models; performing the personalized post-training of neural network models with taking into account the individual SM-settings of concrete users, operators or experts. This will combine the effectiveness of deep learning on huge training bases with partial transparency of reasoning and the possibility of directly taking into account the wishes of users in terms of SM-models, rather than by creating the artificial training bases via artificial augmentation.
35
Brewster, Lauran R., Ali K. Ibrahim, Breanna C. DeGroot, Thomas J. Ostendorf, Hanqi Zhuang, Laurent M. Chérubin, and Matthew J. Ajemian. "Classifying Goliath Grouper (Epinephelus itajara) Behaviors from a Novel, Multi-Sensor Tag." Sensors 21, no. 19 (September 24, 2021): 6392. http://dx.doi.org/10.3390/s21196392.
Full textAbstract:
Inertial measurement unit sensors (IMU; i.e., accelerometer, gyroscope and magnetometer combinations) are frequently fitted to animals to better understand their activity patterns and energy expenditure. Capable of recording hundreds of data points a second, these sensors can quickly produce large datasets that require methods to automate behavioral classification. Here, we describe behaviors derived from a custom-built multi-sensor bio-logging tag attached to Atlantic Goliath grouper (Epinephelus itajara) within a simulated ecosystem. We then compared the performance of two commonly applied machine learning approaches (random forest and support vector machine) to a deep learning approach (convolutional neural network, or CNN) for classifying IMU data from this tag. CNNs are frequently used to recognize activities from IMU data obtained from humans but are less commonly considered for other animals. Thirteen behavioral classes were identified during ethogram development, nine of which were classified. For the conventional machine learning approaches, 187 summary statistics were extracted from the data, including time and frequency domain features. The CNN was fed absolute values obtained from fast Fourier transformations of the raw tri-axial accelerometer, gyroscope and magnetometer channels, with a frequency resolution of 512 data points. Five metrics were used to assess classifier performance; the deep learning approach performed better across all metrics (Sensitivity = 0.962; Specificity = 0.996; F1-score = 0.962; Matthew’s Correlation Coefficient = 0.959; Cohen’s Kappa = 0.833) than both conventional machine learning approaches. Generally, the random forest performed better than the support vector machine. In some instances, a conventional learning approach yielded a higher performance metric for particular classes (e.g., the random forest had a F1-score of 0.971 for backward swimming compared to 0.955 for the CNN). Deep learning approaches could potentially improve behavioral classification from IMU data, beyond that obtained from conventional machine learning methods.
36
Khan, Koffka, and Wayne Goodridge. "Comparative study of One-Shot Learning in Dynamic Adaptive Streaming over HTTP : A Taxonomy-Based Analysis." International Journal of Advanced Networking and Applications 15, no. 01 (2023): 5822–30. http://dx.doi.org/10.35444/ijana.2023.15112.
Full textAbstract:
Dynamic Adaptive Streaming over HTTP (DASH) has revolutionized multimedia content delivery, enabling efficient video streaming over the internet. One-shot learning, a machine learning paradigm that allows recognition of new classes or objects with minimal training examples, holds promise for enhancing DASH systems. In this comparative study, we present a taxonomy-based analysis of one-shot learning techniques in the context of DASH, examining four taxonomies to provide a comprehensive understanding of their applications, evaluation metrics, and datasets. The first taxonomy focuses on categorizing one-shot learning techniques, including siamese networks, metric learning approaches, prototype-based methods, and generative models. This taxonomy reveals the diversity of techniques employed to tackle one-shot learning challenges in DASH environments. The second taxonomy explores the applications of one-shot learning in DASH. It highlights areas such as video quality prediction, buffer management, content adaptation, and bandwidth estimation, shedding light on how one-shot learning can optimize streaming decisions based on limited or single examples. The third taxonomy addresses evaluation metrics for one-shot learning in DASH. It encompasses accuracy-based metrics, generalization metrics, latency-related metrics, and robustness metrics, providing insights into the performance and effectiveness of one-shot learning approaches under various evaluation criteria. The fourth taxonomy delves into dataset characteristics for one-shot learning in DASH. It categorizes datasets into synthetic datasets, real-world datasets, transfer learning datasets, and unconstrained datasets, enabling researchers to select appropriate data sources and evaluate one-shot learning techniques in diverse streaming scenarios. By conducting this taxonomy-based analysis, our study provides researchers and practitioners with a structured framework for understanding and comparing different aspects of one-shot learning in DASH. It highlights the strengths, weaknesses, and potential applications of various techniques, offers guidance on evaluation metrics, and showcases dataset characteristics for benchmarking and future research. Ultimately, this comparative study aims to foster progress in one-shot learning for DASH by facilitating knowledge exchange, inspiring new research directions, and promoting the development of efficient and adaptive multimedia streaming systems over HTTP.
37
Johnson, Gretchen L. "Using a Metric Unit to Help Preservice Teachers Appreciate the Value of Manipulative Materials." Arithmetic Teacher 35, no. 2 (October 1987): 14–20. http://dx.doi.org/10.5951/at.35.2.0014.
Full textAbstract:
Preservice teacher in my elementary mathematic method class often find it difficult to imagine how much help manipulative materials or an activity approach can be to a chi ld in learning a new concept. To help them understand, I teach them the metric ystem-for many an intimidating subject- using the ame materials and approache that would be used with children, although covering the material in a shorter period of time. If the e method help the preservice teachers learn the metric system, then they hould be convinced that the same approaches will work with chi ldren. ln turn, they will be more likely to use manipulatives in their own classrooms in the future.
38
Litvynchuk, Andrey, and Lesia Baranovska. "IMPROVING FACE RECOGNITION MODELS USING METRIC LEARNING, LEARNING RATE SCHEDULERS, AND AUGMENTATIONS." Journal of Automation and Information sciences 6 (November 1, 2021): 93–101. http://dx.doi.org/10.34229/1028-0979-2021-6-9.
Full textAbstract:
Face recognition is one of the main tasks of computer vision, which is relevant due to its practical significance and great interest of wide range of scientists. It has many applications, which has led to a huge amount of research in this area. And although research in the field has been going on since the beginning of the computer vision, good results could be achieved only with the help of convolutional neural networks. In this work, a comparative analysis of facial recognition methods before convolutional neural networks was performed. A metric learning approach, augmentations and learning rate schedulers are considered. There were performed bunch of experiments and comparative analysis of the considered methods of improvement of convolutional neural networks. As a result a universal algorithm for training the face recognition model was obtained. In this work, we used SE-ResNet50 as the only neural network for experiments. Metric learning is a method by which it is possible to achieve good accuracy in face recognition. Overfitting is a big problem of neural networks, in particular because they have too many parameters and usually not enough data to guarantee the generalization of the model. Additional data labeling can be time-consuming and expensive, so there is such an approach as augmentation. Augmentations artificially increase the training dataset, so as expected, this method improved the results relative to the original experiment in all experiments. Different degrees and more aggressive forms of augmentation in this work led to better results. As expected, the best learning rate scheduler was cosine scheduler with warm-ups and restarts. This schedule has few parameters, so it is also easy to use. In general, using different approaches, we were able to obtain an accuracy of 93,5 %, which is 22 % better than the baseline experiment. In the following studies, it is planned to consider improving not only the model of facial recognition, but also detection. The accuracy of face detection directly depends on the quality of face recognition.
39
Schleif, Frank-Michael, and Peter Tino. "Indefinite Proximity Learning: A Review." Neural Computation 27, no. 10 (October 2015): 2039–96. http://dx.doi.org/10.1162/neco_a_00770.
Full textAbstract:
Efficient learning of a data analysis task strongly depends on the data representation. Most methods rely on (symmetric) similarity or dissimilarity representations by means of metric inner products or distances, providing easy access to powerful mathematical formalisms like kernel or branch-and-bound approaches. Similarities and dissimilarities are, however, often naturally obtained by nonmetric proximity measures that cannot easily be handled by classical learning algorithms. Major efforts have been undertaken to provide approaches that can either directly be used for such data or to make standard methods available for these types of data. We provide a comprehensive survey for the field of learning with nonmetric proximities. First, we introduce the formalism used in nonmetric spaces and motivate specific treatments for nonmetric proximity data. Second, we provide a systematization of the various approaches. For each category of approaches, we provide a comparative discussion of the individual algorithms and address complexity issues and generalization properties. In a summarizing section, we provide a larger experimental study for the majority of the algorithms on standard data sets. We also address the problem of large-scale proximity learning, which is often overlooked in this context and of major importance to make the method relevant in practice. The algorithms we discuss are in general applicable for proximity-based clustering, one-class classification, classification, regression, and embedding approaches. In the experimental part, we focus on classification tasks.
40
MARKOV, ZDRAVKO. "AN ALGEBRAIC APPROACH TO INDUCTIVE LEARNING." International Journal on Artificial Intelligence Tools 10, no. 01n02 (March 2001): 257–72. http://dx.doi.org/10.1142/s0218213001000519.
Full textAbstract:
The paper presents a framework to induction of concept hierarchies based on consistent integration of metric and similarity-based approaches. The hierarchies used are subsumption lattices induced by the least general generalization operator (lgg) commonly used in inductive learning. Using some basic results from lattice theory the paper introduces a semantic distance measure between objects in concept hierarchies and discusses its applications for solving concept learning and conceptual clustering tasks. Experiments with well known ML datasets represented in three types of languages - propositional (attribute-value), atomic formulae and Horn clauses, are also presented.
41
Wang, Weijie, Hong Zhao, Yikun Yang, YouKang Chang, and Haojie You. "Few-shot short utterance speaker verification using meta-learning." PeerJ Computer Science 9 (April 21, 2023): e1276. http://dx.doi.org/10.7717/peerj-cs.1276.
Full textAbstract:
Short utterance speaker verification (SV) in the actual application is the task of accepting or rejecting the identity claim of a speaker based on a few enrollment utterances. Traditional methods have used deep neural networks to extract speaker representations for verification. Recently, several meta-learning approaches have learned a deep distance metric to distinguish speakers within meta-tasks. Among them, a prototypical network learns a metric space that may be used to compute the distance to the prototype center of speakers, in order to classify speaker identity. We use emphasized channel attention, propagation and aggregation in TDNN (ECAPA-TDNN) to implement the necessary function for the prototypical network, which is a nonlinear mapping from the input space to the metric space for either few-shot SV task. In addition, optimizing only for speakers in given meta-tasks cannot be sufficient to learn distinctive speaker features. Thus, we used an episodic training strategy, in which the classes of the support and query sets correspond to the classes of the entire training set, further improving the model performance. The proposed model outperforms comparison models on the VoxCeleb1 dataset and has a wide range of practical applications.
42
Dou, Jason Xiaotian, Lei Luo, and Raymond Mingrui Yang. "An Optimal Transport Approach to Deep Metric Learning (Student Abstract)." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 11 (June 28, 2022): 12935–36. http://dx.doi.org/10.1609/aaai.v36i11.21604.
Full textAbstract:
Capturing visual similarity among images is the core of many computer vision and pattern recognition tasks. This problem can be formulated in such a paradigm called metric learning. Most research in the area has been mainly focusing on improving the loss functions and similarity measures. However, due to the ignoring of geometric structure, existing methods often lead to sub-optimal results. Thus, several recent research methods took advantage of Wasserstein distance between batches of samples to characterize the spacial geometry. Although these approaches can achieve enhanced performance, the aggregation over batches definitely hinders Wasserstein distance's superior measure capability and leads to high computational complexity. To address this limitation, we propose a novel Deep Wasserstein Metric Learning framework, which employs Wasserstein distance to precisely capture the relationship among various images under ranking-based loss functions such as contrastive loss and triplet loss. Our method directly computes the distance between images, considering the geometry at a finer granularity than batch level. Furthermore, we introduce a new efficient algorithm using Sinkhorn approximation and Wasserstein measure coreset. The experimental results demonstrate the improvements of our framework over various baselines in different applications and benchmark datasets.
43
Coombes, Caitlin E., Zachary B. Abrams, Suli Li, Lynne V. Abruzzo, and Kevin R. Coombes. "Unsupervised machine learning and prognostic factors of survival in chronic lymphocytic leukemia." Journal of the American Medical Informatics Association 27, no. 7 (June 1, 2020): 1019–27. http://dx.doi.org/10.1093/jamia/ocaa060.
Full textAbstract:
Abstract Objective Unsupervised machine learning approaches hold promise for large-scale clinical data. However, the heterogeneity of clinical data raises new methodological challenges in feature selection, choosing a distance metric that captures biological meaning, and visualization. We hypothesized that clustering could discover prognostic groups from patients with chronic lymphocytic leukemia, a disease that provides biological validation through well-understood outcomes. Methods To address this challenge, we applied k-medoids clustering with 10 distance metrics to 2 experiments (“A” and “B”) with mixed clinical features collapsed to binary vectors and visualized with both multidimensional scaling and t-stochastic neighbor embedding. To assess prognostic utility, we performed survival analysis using a Cox proportional hazard model, log-rank test, and Kaplan-Meier curves. Results In both experiments, survival analysis revealed a statistically significant association between clusters and survival outcomes (A: overall survival, P = .0164; B: time from diagnosis to treatment, P = .0039). Multidimensional scaling separated clusters along a gradient mirroring the order of overall survival. Longer survival was associated with mutated immunoglobulin heavy-chain variable region gene (IGHV) status, absent Zap 70 expression, female sex, and younger age. Conclusions This approach to mixed-type data handling and selection of distance metric captured well-understood, binary, prognostic markers in chronic lymphocytic leukemia (sex, IGHV mutation status, ZAP70 expression status) with high fidelity.
44
Steck, Harald, Linas Baltrunas, Ehtsham Elahi, Dawen Liang, Yves Raimond, and Justin Basilico. "Deep Learning for Recommender Systems: A Netflix Case Study." AI Magazine 42, no. 3 (November 20, 2021): 7–18. http://dx.doi.org/10.1609/aimag.v42i3.18140.
Full textAbstract:
Deep learning has profoundly impacted many areas of machine learning. However, it took a while for its impact to be felt in the field of recommender systems. In this article, we outline some of the challenges encountered and lessons learned in using deep learning for recommender systems at Netflix. We first provide an overview of the various recommendation tasks on the Netflix service. We found that different model architectures excel at different tasks. Even though many deep-learning models can be understood as extensions of existing (simple) recommendation algorithms, we initially did not observe significant improvements in performance over well-tuned non-deep-learning approaches. Only when we added numerous features of heterogeneous types to the input data, deep-learning models did start to shine in our setting. We also observed that deep-learning methods can exacerbate the problem of offline–online metric (mis-)alignment. After addressing these challenges, deep learning has ultimately resulted in large improvements to our recommendations as measured by both offline and online metrics. On the practical side, integrating deep-learning toolboxes in our system has made it faster and easier to implement and experiment with both deep-learning and non-deep-learning approaches for various recommendation tasks. We conclude this article by summarizing our take-aways that may generalize to other applications beyond Netflix.
45
Jawanpuria, Pratik, Arjun Balgovind, Anoop Kunchukuttan, and Bamdev Mishra. "Learning Multilingual Word Embeddings in Latent Metric Space: A Geometric Approach." Transactions of the Association for Computational Linguistics 7 (November 2019): 107–20. http://dx.doi.org/10.1162/tacl_a_00257.
Full textAbstract:
We propose a novel geometric approach for learning bilingual mappings given monolingual embeddings and a bilingual dictionary. Our approach decouples the source-to-target language transformation into (a) language-specific rotations on the original embeddings to align them in a common, latent space, and (b) a language-independent similarity metric in this common space to better model the similarity between the embeddings. Overall, we pose the bilingual mapping problem as a classification problem on smooth Riemannian manifolds. Empirically, our approach outperforms previous approaches on the bilingual lexicon induction and cross-lingual word similarity tasks. We next generalize our framework to represent multiple languages in a common latent space. Language-specific rotations for all the languages and a common similarity metric in the latent space are learned jointly from bilingual dictionaries for multiple language pairs. We illustrate the effectiveness of joint learning for multiple languages in an indirect word translation setting.
46
Orozco-Arias, Simon, Johan S. Piña, Reinel Tabares-Soto, Luis F. Castillo-Ossa, Romain Guyot, and Gustavo Isaza. "Measuring Performance Metrics of Machine Learning Algorithms for Detecting and Classifying Transposable Elements." Processes 8, no. 6 (May 27, 2020): 638. http://dx.doi.org/10.3390/pr8060638.
Full textAbstract:
Because of the promising results obtained by machine learning (ML) approaches in several fields, every day is more common, the utilization of ML to solve problems in bioinformatics. In genomics, a current issue is to detect and classify transposable elements (TEs) because of the tedious tasks involved in bioinformatics methods. Thus, ML was recently evaluated for TE datasets, demonstrating better results than bioinformatics applications. A crucial step for ML approaches is the selection of metrics that measure the realistic performance of algorithms. Each metric has specific characteristics and measures properties that may be different from the predicted results. Although the most commonly used way to compare measures is by using empirical analysis, a non-result-based methodology has been proposed, called measure invariance properties. These properties are calculated on the basis of whether a given measure changes its value under certain modifications in the confusion matrix, giving comparative parameters independent of the datasets. Measure invariance properties make metrics more or less informative, particularly on unbalanced, monomodal, or multimodal negative class datasets and for real or simulated datasets. Although several studies applied ML to detect and classify TEs, there are no works evaluating performance metrics in TE tasks. Here, we analyzed 26 different metrics utilized in binary, multiclass, and hierarchical classifications, through bibliographic sources, and their invariance properties. Then, we corroborated our findings utilizing freely available TE datasets and commonly used ML algorithms. Based on our analysis, the most suitable metrics for TE tasks must be stable, even using highly unbalanced datasets, multimodal negative class, and training datasets with errors or outliers. Based on these parameters, we conclude that the F1-score and the area under the precision-recall curve are the most informative metrics since they are calculated based on other metrics, providing insight into the development of an ML application.
47
Szostak, Daniel, Adam Włodarczyk, and Krzysztof Walkowiak. "Machine Learning Classification and Regression Approaches for Optical Network Traffic Prediction." Electronics 10, no. 13 (June 30, 2021): 1578. http://dx.doi.org/10.3390/electronics10131578.
Full textAbstract:
Rapid growth of network traffic causes the need for the development of new network technologies. Artificial intelligence provides suitable tools to improve currently used network optimization methods. In this paper, we propose a procedure for network traffic prediction. Based on optical networks’ (and other network technologies) characteristics, we focus on the prediction of fixed bitrate levels called traffic levels. We develop and evaluate two approaches based on different supervised machine learning (ML) methods—classification and regression. We examine four different ML models with various selected features. The tested datasets are based on real traffic patterns provided by the Seattle Internet Exchange Point (SIX). Obtained results are analyzed using a new quality metric, which allows researchers to find the best forecasting algorithm in terms of network resources usage and operational costs. Our research shows that regression provides better results than classification in case of all analyzed datasets. Additionally, the final choice of the most appropriate ML algorithm and model should depend on the network operator expectations.
48
Khan, Sarwar, Jun-Cheng Chen, Wen-Hung Liao, and Chu-Song Chen. "Towards Adversarial Robustness for Multi-Mode Data through Metric Learning." Sensors 23, no. 13 (July 5, 2023): 6173. http://dx.doi.org/10.3390/s23136173.
Full textAbstract:
Adversarial attacks have become one of the most serious security issues in widely used deep neural networks. Even though real-world datasets usually have large intra-variations or multiple modes, most adversarial defense methods, such as adversarial training, which is currently one of the most effective defense methods, mainly focus on the single-mode setting and thus fail to capture the full data representation to defend against adversarial attacks. To confront this challenge, we propose a novel multi-prototype metric learning regularization for adversarial training which can effectively enhance the defense capability of adversarial training by preventing the latent representation of the adversarial example changing a lot from its clean one. With extensive experiments on CIFAR10, CIFAR100, MNIST, and Tiny ImageNet, the evaluation results show the proposed method improves the performance of different state-of-the-art adversarial training methods without additional computational cost. Furthermore, besides Tiny ImageNet, in the multi-prototype CIFAR10 and CIFAR100 where we reorganize the whole datasets of CIFAR10 and CIFAR100 into two and ten classes, respectively, the proposed method outperforms the state-of-the-art approach by 2.22% and 1.65%, respectively. Furthermore, the proposed multi-prototype method also outperforms its single-prototype version and other commonly used deep metric learning approaches as regularization for adversarial training and thus further demonstrates its effectiveness.
49
Xue, Wanqi, and Wei Wang. "One-Shot Image Classification by Learning to Restore Prototypes." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (April 3, 2020): 6558–65. http://dx.doi.org/10.1609/aaai.v34i04.6130.
Full textAbstract:
One-shot image classification aims to train image classifiers over the dataset with only one image per category. It is challenging for modern deep neural networks that typically require hundreds or thousands of images per class. In this paper, we adopt metric learning for this problem, which has been applied for few- and many-shot image classification by comparing the distance between the test image and the center of each class in the feature space. However, for one-shot learning, the existing metric learning approaches would suffer poor performance because the single training image may not be representative of the class. For example, if the image is far away from the class center in the feature space, the metric-learning based algorithms are unlikely to make correct predictions for the test images because the decision boundary is shifted by this noisy image. To address this issue, we propose a simple yet effective regression model, denoted by RestoreNet, which learns a class agnostic transformation on the image feature to move the image closer to the class center in the feature space. Experiments demonstrate that RestoreNet obtains superior performance over the state-of-the-art methods on a broad range of datasets. Moreover, RestoreNet can be easily combined with other methods to achieve further improvement.
50
Schneider, Petra, Michael Biehl, and Barbara Hammer. "Distance Learning in Discriminative Vector Quantization." Neural Computation 21, no. 10 (October 2009): 2942–69. http://dx.doi.org/10.1162/neco.2009.10-08-892.
Full textAbstract:
Discriminative vector quantization schemes such as learning vector quantization (LVQ) and extensions thereof offer efficient and intuitive classifiers based on the representation of classes by prototypes. The original methods, however, rely on the Euclidean distance corresponding to the assumption that the data can be represented by isotropic clusters. For this reason, extensions of the methods to more general metric structures have been proposed, such as relevance adaptation in generalized LVQ (GLVQ) and matrix learning in GLVQ. In these approaches, metric parameters are learned based on the given classification task such that a data-driven distance measure is found. In this letter, we consider full matrix adaptation in advanced LVQ schemes. In particular, we introduce matrix learning to a recent statistical formalization of LVQ, robust soft LVQ, and we compare the results on several artificial and real-life data sets to matrix learning in GLVQ, a derivation of LVQ-like learning based on a (heuristic) cost function. In all cases, matrix adaptation allows a significant improvement of the classification accuracy. Interestingly, however, the principled behavior of the models with respect to prototype locations and extracted matrix dimensions shows several characteristic differences depending on the data sets.