Journal articles: 'Deep Unsupervised Learning'

1

Zhao, Tingting, Zifeng Wang, Aria Masoomi, and Jennifer Dy. "Deep Bayesian Unsupervised Lifelong Learning." Neural Networks 149 (May 2022): 95–106. http://dx.doi.org/10.1016/j.neunet.2022.02.001.

Full text

APA, Harvard, Vancouver, ISO, and other styles

2

Banzi, Jamal, Isack Bulugu, and Zhongfu Ye. "Deep Predictive Neural Network: Unsupervised Learning for Hand Pose Estimation." International Journal of Machine Learning and Computing 9, no. 4 (August 2019): 432–39. http://dx.doi.org/10.18178/ijmlc.2019.9.4.822.

Full text

APA, Harvard, Vancouver, ISO, and other styles

3

Fong, A. C. M., and G. Hong. "Boosted Supervised Intensional Learning Supported by Unsupervised Learning." International Journal of Machine Learning and Computing 11, no. 2 (March 2021): 98–102. http://dx.doi.org/10.18178/ijmlc.2021.11.2.1020.

Full text

Abstract:

Traditionally, supervised machine learning (ML) algorithms rely heavily on large sets of annotated data. This is especially true for deep learning (DL) neural networks, which need huge annotated data sets for good performance. However, large volumes of annotated data are not always readily available. In addition, some of the best performing ML and DL algorithms lack explainability – it is often difficult even for domain experts to interpret the results. This is an important consideration especially in safety-critical applications, such as AI-assisted medical endeavors, in which a DL’s failure mode is not well understood. This lack of explainability also increases the risk of malicious attacks by adversarial actors because these actions can become obscured in the decision-making process that lacks transparency. This paper describes an intensional learning approach which uses boosting to enhance prediction performance while minimizing reliance on availability of annotated data. The intensional information is derived from an unsupervised learning preprocessing step involving clustering. Preliminary evaluation on the MNIST data set has shown encouraging results. Specifically, using the proposed approach, it is now possible to achieve similar accuracy result as extensional learning alone while using only a small fraction of the original training data set.

APA, Harvard, Vancouver, ISO, and other styles

4

Huang, Jiabo, Qi Dong, Shaogang Gong, and Xiatian Zhu. "Unsupervised Deep Learning via Affinity Diffusion." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 07 (April 3, 2020): 11029–36. http://dx.doi.org/10.1609/aaai.v34i07.6757.

Full text

Abstract:

Convolutional neural networks (CNNs) have achieved unprecedented success in a variety of computer vision tasks. However, they usually rely on supervised model learning with the need for massive labelled training data, limiting dramatically their usability and deployability in real-world scenarios without any labelling budget. In this work, we introduce a general-purpose unsupervised deep learning approach to deriving discriminative feature representations. It is based on self-discovering semantically consistent groups of unlabelled training samples with the same class concepts through a progressive affinity diffusion process. Extensive experiments on object image classification and clustering show the performance superiority of the proposed method over the state-of-the-art unsupervised learning models using six common image recognition benchmarks including MNIST, SVHN, STL10, CIFAR10, CIFAR100 and ImageNet.

APA, Harvard, Vancouver, ISO, and other styles

5

Sanakoyeu, Artsiom, Miguel A. Bautista, and Björn Ommer. "Deep unsupervised learning of visual similarities." Pattern Recognition 78 (June 2018): 331–43. http://dx.doi.org/10.1016/j.patcog.2018.01.036.

Full text

APA, Harvard, Vancouver, ISO, and other styles

6

Yousefi-Azar, Mahmood, and Len Hamey. "Text summarization using unsupervised deep learning." Expert Systems with Applications 68 (February 2017): 93–105. http://dx.doi.org/10.1016/j.eswa.2016.10.017.

Full text

APA, Harvard, Vancouver, ISO, and other styles

7

Liu, Dong, Chengjian Sun, Chenyang Yang, and Lajos Hanzo. "Optimizing Wireless Systems Using Unsupervised and Reinforced-Unsupervised Deep Learning." IEEE Network 34, no. 4 (July 2020): 270–77. http://dx.doi.org/10.1109/mnet.001.1900517.

Full text

APA, Harvard, Vancouver, ISO, and other styles

8

Xuejun Zhang, Xuejun Zhang, Jiyang Gai Xuejun Zhang, Zhili Ma Jiyang Gai, Jinxiong Zhao Zhili Ma, Hongzhong Ma Jinxiong Zhao, Fucun He Hongzhong Ma, and Tao Ju Fucun He. "Exploring Unsupervised Learning with Clustering and Deep Autoencoder to Detect DDoS Attack." 電腦學刊 33, no. 4 (August 2022): 029–44. http://dx.doi.org/10.53106/199115992022083304003.

Full text

Abstract:

<p>With the proliferation of services available on the Internet, network attacks have become one of the seri-ous issues. The distributed denial of service (DDoS) attack is such a devastating attack, which poses an enormous threat to network communication and applications and easily disrupts services. To defense against DDoS attacks effectively, this paper proposes a novel DDoS attack detection method that trains detection models in an unsupervised learning manner using preprocessed and unlabeled normal network traffic data, which can not only avoid the impact of unbalanced training data on the detection model per-formance but also detect unknown attacks. Specifically, the proposed method firstly uses Balanced Itera-tive Reducing and Clustering Using Hierarchies algorithm (BIRCH) to pre-cluster the normal network traf-fic data, and then explores autoencoder (AE) to build the detection model in an unsupervised manner based on the cluster subsets. In order to verify the performance of our method, we perform experiments on benchmark network intrusion detection datasets KDDCUP99 and UNSWNB15. The results show that, compared with the state-of-the-art DDoS detection models that used supervised learning and unsuper-vised learning, our proposed method achieves better performance in terms of detection accuracy rate and false positive rate (FPR).</p> <p> </p>

APA, Harvard, Vancouver, ISO, and other styles

9

Kim, Seonghyeon, Sunjin Jung, Kwanggyoon Seo, Roger Blanco i Ribera, and Junyong Noh. "Deep Learning‐Based Unsupervised Human Facial Retargeting." Computer Graphics Forum 40, no. 7 (October 2021): 45–55. http://dx.doi.org/10.1111/cgf.14400.

Full text

APA, Harvard, Vancouver, ISO, and other styles

10

Li, Changsheng, Rongqing Li, Ye Yuan, Guoren Wang, and Dong Xu. "Deep Unsupervised Active Learning via Matrix Sketching." IEEE Transactions on Image Processing 30 (2021): 9280–93. http://dx.doi.org/10.1109/tip.2021.3124317.

Full text

APA, Harvard, Vancouver, ISO, and other styles

11

Gomes, Chamal, Zhuo Jin, and Hailiang Yang. "Insurance fraud detection with unsupervised deep learning." Journal of Risk and Insurance 88, no. 3 (July 26, 2021): 591–624. http://dx.doi.org/10.1111/jori.12359.

Full text

APA, Harvard, Vancouver, ISO, and other styles

12

Lin, Kevin, Jiwen Lu, Chu-Song Chen, Jie Zhou, and Ming-Ting Sun. "Unsupervised Deep Learning of Compact Binary Descriptors." IEEE Transactions on Pattern Analysis and Machine Intelligence 41, no. 6 (June 1, 2019): 1501–14. http://dx.doi.org/10.1109/tpami.2018.2833865.

Full text

APA, Harvard, Vancouver, ISO, and other styles

13

Chen, Changlu, Chaoxi Niu, Xia Zhan, and Kun Zhan. "Generative approach to unsupervised deep local learning." Journal of Electronic Imaging 28, no. 04 (July 10, 2019): 1. http://dx.doi.org/10.1117/1.jei.28.4.043005.

Full text

APA, Harvard, Vancouver, ISO, and other styles

14

Zheng, Dihan, Chenglong Bao, Zuoqiang Shi, Haibin Ling, and Kaisheng Ma. "Unsupervised Deep Learning Meets Chan-Vese Model." CSIAM Transactions on Applied Mathematics 3, no. 4 (June 2022): 662–91. http://dx.doi.org/10.4208/csiam-am.so-2021-0049.

Full text

APA, Harvard, Vancouver, ISO, and other styles

15

Cui, Jianan, Kuang Gong, Ning Guo, Chenxi Wu, Xiaxia Meng, Kyungsang Kim, Kun Zheng, et al. "PET image denoising using unsupervised deep learning." European Journal of Nuclear Medicine and Molecular Imaging 46, no. 13 (August 29, 2019): 2780–89. http://dx.doi.org/10.1007/s00259-019-04468-4.

Full text

APA, Harvard, Vancouver, ISO, and other styles

16

Boccagna, Roberto, Maurizio Bottini, Massimo Petracca, Alessia Amelio, and Guido Camata. "Unsupervised Deep Learning for Structural Health Monitoring." Big Data and Cognitive Computing 7, no. 2 (May 17, 2023): 99. http://dx.doi.org/10.3390/bdcc7020099.

Full text

Abstract:

In the last few decades, structural health monitoring has gained relevance in the context of civil engineering, and much effort has been made to automate the process of data acquisition and analysis through the use of data-driven methods. Currently, the main issues arising in automated monitoring processing regard the establishment of a robust approach that covers all intermediate steps from data acquisition to output production and interpretation. To overcome this limitation, we introduce a dedicated artificial-intelligence-based monitoring approach for the assessment of the health conditions of structures in near-real time. The proposed approach is based on the construction of an unsupervised deep learning algorithm, with the aim of establishing a reliable method of anomaly detection for data acquired from sensors positioned on buildings. After preprocessing, the data are fed into various types of artificial neural network autoencoders, which are trained to produce outputs as close as possible to the inputs. We tested the proposed approach on data generated from an OpenSees numerical model of a railway bridge and data acquired from physical sensors positioned on the Historical Tower of Ravenna (Italy). The results show that the approach actually flags the data produced when damage scenarios are activated in the OpenSees model as coming from a damaged structure. The proposed method is also able to reliably detect anomalous structural behaviors of the tower, preventing critical scenarios. Compared to other state-of-the-art methods for anomaly detection, the proposed approach shows very promising results.

APA, Harvard, Vancouver, ISO, and other styles

17

Zheng, Huan, Tongyao Pang, and Hui Ji. "Unsupervised Deep Video Denoising with Untrained Network." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 3 (June 26, 2023): 3651–59. http://dx.doi.org/10.1609/aaai.v37i3.25476.

Full text

Abstract:

Deep learning has become a prominent tool for video denoising. However, most existing deep video denoising methods require supervised training using noise-free videos. Collecting noise-free videos can be costly and challenging in many applications. Therefore, this paper aims to develop an unsupervised deep learning method for video denoising that only uses a single test noisy video for training. To achieve this, an unsupervised loss function is presented that provides an unbiased estimator of its supervised counterpart defined on noise-free video. Additionally, a temporal attention mechanism is proposed to exploit redundancy among frames. The experiments on video denoising demonstrate that the proposed unsupervised method outperforms existing unsupervised methods and remains competitive against recent supervised deep learning methods.

APA, Harvard, Vancouver, ISO, and other styles

18

Ajay, P., B. Nagaraj, R. Arun Kumar, Ruihang Huang, and P. Ananthi. "Unsupervised Hyperspectral Microscopic Image Segmentation Using Deep Embedded Clustering Algorithm." Scanning 2022 (June 6, 2022): 1–9. http://dx.doi.org/10.1155/2022/1200860.

Full text

Abstract:

Hyperspectral microscopy in biology and minerals, unsupervised deep learning neural network denoising SRS photos: hyperspectral resolution enhancement and denoising one hyperspectral picture is enough to teach unsupervised method. An intuitive chemical species map for a lithium ore sample is produced using k -means clustering. Many researchers are now interested in biosignals. Uncertainty limits the algorithms’ capacity to evaluate these signals for further information. Even while AI systems can answer puzzles, they remain limited. Deep learning is used when machine learning is inefficient. Supervised learning needs a lot of data. Deep learning is vital in modern AI. Supervised learning requires a large labeled dataset. The selection of parameters prevents over- or underfitting. Unsupervised learning is used to overcome the challenges outlined above (performed by the clustering algorithm). To accomplish this, two processing processes were used: (1) utilizing nonlinear deep learning networks to turn data into a latent feature space ( Z ). The Kullback–Leibler divergence is used to test the objective function convergence. This article explores a novel research on hyperspectral microscopic picture using deep learning and effective unsupervised learning.

APA, Harvard, Vancouver, ISO, and other styles

19

Xu, Mingle, Sook Yoon, Jaesu Lee, and Dong Sun Park. "Unsupervised Transfer Learning for Plant Anomaly Recognition." Korean Institute of Smart Media 11, no. 4 (May 31, 2022): 30–37. http://dx.doi.org/10.30693/smj.2022.11.4.30.

Full text

Abstract:

Disease threatens plant growth and recognizing the type of disease is essential to making a remedy. In recent years, deep learning has witnessed a significant improvement for this task, however, a large volume of labeled images is one of the requirements to get decent performance. But annotated images are difficult and expensive to obtain in the agricultural field. Therefore, designing an efficient and effective strategy is one of the challenges in this area with few labeled data. Transfer learning, assuming taking knowledge from a source domain to a target domain, is borrowed to address this issue and observed comparable results. However, current transfer learning strategies can be regarded as a supervised method as it hypothesizes that there are many labeled images in a source domain. In contrast, unsupervised transfer learning, using only images in a source domain, gives more convenience as collecting images is much easier than annotating. In this paper, we leverage unsupervised transfer learning to perform plant disease recognition, by which we achieve a better performance than supervised transfer learning in many cases. Besides, a vision transformer with a bigger model capacity than convolution is utilized to have a better-pretrained feature space. With the vision transformer-based unsupervised transfer learning, we achieve better results than current works in two datasets. Especially, we obtain 97.3% accuracy with only 30 training images for each class in the Plant Village dataset. We hope that our work can encourage the community to pay attention to vision transformer-based unsupervised transfer learning in the agricultural field when with few labeled images.

APA, Harvard, Vancouver, ISO, and other styles

20

Yang, Yang, Yi-Feng Wu, De-Chuan Zhan, Zhi-Bin Liu, and Yuan Jiang. "Deep Robust Unsupervised Multi-Modal Network." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 5652–59. http://dx.doi.org/10.1609/aaai.v33i01.33015652.

Full text

Abstract:

In real-world applications, data are often with multiple modalities, and many multi-modal learning approaches are proposed for integrating the information from different sources. Most of the previous multi-modal methods utilize the modal consistency to reduce the complexity of the learning problem, therefore the modal completeness needs to be guaranteed. However, due to the data collection failures, self-deficiencies, and other various reasons, multi-modal instances are often incomplete in real applications, and have the inconsistent anomalies even in the complete instances, which jointly result in the inconsistent problem. These degenerate the multi-modal feature learning performance, and will finally affect the generalization abilities in different tasks. In this paper, we propose a novel Deep Robust Unsupervised Multi-modal Network structure (DRUMN) for solving this real problem within a unified framework. The proposed DRUMN can utilize the extrinsic heterogeneous information from unlabeled data against the insufficiency caused by the incompleteness. On the other hand, the inconsistent anomaly issue is solved with an adaptive weighted estimation, rather than adjusting the complex thresholds. As DRUMN can extract the discriminative feature representations for each modality, experiments on real-world multimodal datasets successfully validate the effectiveness of our proposed method.

APA, Harvard, Vancouver, ISO, and other styles

21

Zhao, Xiaoli, and Minping Jia. "A novel unsupervised deep learning network for intelligent fault diagnosis of rotating machinery." Structural Health Monitoring 19, no. 6 (January 9, 2020): 1745–63. http://dx.doi.org/10.1177/1475921719897317.

Full text

Abstract:

Generally, the health conditions of rotating machinery are complicated and changeable. Meanwhile, its fault labeled information is mostly unknown. Therefore, it is man-sized to automatically capture the useful fault labeled information from the monitoring raw vibration signals. That is to say, the intelligent unsupervised learning approach has a significant influence on fault diagnosis of rotating machinery. In this study, a span-new unsupervised deep learning network can be constructed based on the proposed feature extractor (L12 sparse filtering (L12SF)) and the designed clustering extractor (Weighted Euclidean Affinity Propagation) for resolving the issue that the acquisition of fault sample labeled information is burdensome, yet costly. Naturally, the novel intelligent fault diagnosis method of rotating machinery based on unsupervised deep learning network is first presented in this study. Thereinto, the proposed unsupervised deep learning network consists of two layers of unsupervised feature extractor (L12SF) and one layer of unsupervised clustering (Weighted Euclidean Affinity Propagation). L12SF can improve the regularization performance of sparse filtering, and Weighted Euclidean Affinity Propagation can get rid of the traditional Euclidean distance in affinity propagation that cannot highlight the contribution of different features in fault clustering. To make a long story short, the frequency spectrum signals are first entered into the constructed unsupervised deep learning network for fault feature representation; afterward, the unsupervised feature learning and unsupervised fault classification of rotating machinery can be implemented. The superiority of the proposed algorithms and method is validated by two cases of rolling bearing fault dataset. Ultimately, the proposed unsupervised fault diagnosis method can provide a theoretical basis for the development of intelligent unsupervised fault diagnosis technology for rotating machinery.

APA, Harvard, Vancouver, ISO, and other styles

22

Lin, Yi-Nan, Tsang-Yen Hsieh, Cheng-Ying Yang, Victor RL Shen, Tony Tong-Ying Juang, and Wen-Hao Chen. "Deep Petri nets of unsupervised and supervised learning." Measurement and Control 53, no. 7-8 (June 9, 2020): 1267–77. http://dx.doi.org/10.1177/0020294020923375.

Full text

Abstract:

Artificial intelligence is one of the hottest research topics in computer science. In general, when it comes to the needs to perform deep learning, the most intuitive and unique implementation method is to use neural network. But there are two shortcomings in neural network. First, it is not easy to be understood. When encountering the needs for implementation, it often requires a lot of relevant research efforts to implement the neural network. Second, the structure is complex. When constructing a perfect learning structure, in order to achieve the fully defined connection between nodes, the overall structure becomes complicated. It is hard for developers to track the parameter changes inside. Therefore, the goal of this article is to provide a more streamlined method so as to perform deep learning. A modified high-level fuzzy Petri net, called deep Petri net, is used to perform deep learning, in an attempt to propose a simple and easy structure and to track parameter changes, with faster speed than the deep neural network. The experimental results have shown that the deep Petri net performs better than the deep neural network.

APA, Harvard, Vancouver, ISO, and other styles

23

Aversa, Rossella, Piero Coronica, Cristiano De Nobili, and Stefano Cozzini. "Deep Learning, Feature Learning, and Clustering Analysis for SEM Image Classification." Data Intelligence 2, no. 4 (October 2020): 513–28. http://dx.doi.org/10.1162/dint_a_00062.

Full text

Abstract:

In this paper, we report upon our recent work aimed at improving and adapting machine learning algorithms to automatically classify nanoscience images acquired by the Scanning Electron Microscope (SEM). This is done by coupling supervised and unsupervised learning approaches. We first investigate supervised learning on a ten-category data set of images and compare the performance of the different models in terms of training accuracy. Then, we reduce the dimensionality of the features through autoencoders to perform unsupervised learning on a subset of images in a selected range of scales (from 1 μm to 2 μm). Finally, we compare different clustering methods to uncover intrinsic structures in the images.

APA, Harvard, Vancouver, ISO, and other styles

24

Liu, MengYang, MingJun Li, and XiaoYang Zhang. "The Application of the Unsupervised Migration Method Based on Deep Learning Model in the Marketing Oriented Allocation of High Level Accounting Talents." Computational Intelligence and Neuroscience 2022 (June 6, 2022): 1–10. http://dx.doi.org/10.1155/2022/5653942.

Full text

Abstract:

Deep learning is a branch of machine learning that uses neural networks to mimic the behaviour of the human brain. Various types of models are used in deep learning technology. This article will look at two important models and especially concentrate on unsupervised learning methodology. The two important models are as follows: the supervised and unsupervised models. The main difference is the method of training that they undergo. Supervised models are provided with training on a particular dataset and its outcome. In the case of unsupervised models, only input data is given, and there is no set outcome from which they can learn. The predicting/forecasting column is not present in an unsupervised model, unlike in the supervised model. Supervised models use regression to predict continuous quantities and classification to predict discrete class labels; unsupervised models use clustering to group similar models and association learning to find associations between items. Unsupervised migration is a combination of the unsupervised learning method and migration. In unsupervised learning, there is no need to supervise the models. Migration is an effective tool in processing and imaging data. Unsupervised learning allows the model to work independently to discover patterns and information that were previously undetected. It mainly works on unlabeled data. Unsupervised learning can achieve more complex processing tasks when compared to supervised learning. The unsupervised learning method is more unpredictable when compared with other types of learning methods. Some of the popular unsupervised learning algorithms include k-means clustering, hierarchal clustering, Apriori algorithm, clustering, anomaly detection, association mining, neural networks, etc. In this research article, we implement this particular deep learning model in the marketing oriented asset allocation of high level accounting talents. When the proposed unsupervised migration algorithm was compared to the existing Fractional Hausdorff Grey Model, it was discovered that the proposed system provided 99.12% accuracy by the high level accounting talented candidate in market-oriented asset allocation.

APA, Harvard, Vancouver, ISO, and other styles

25

Liu, MengYang, MingJun Li, and XiaoYang Zhang. "The Application of the Unsupervised Migration Method Based on Deep Learning Model in the Marketing Oriented Allocation of High Level Accounting Talents." Computational Intelligence and Neuroscience 2022 (June 6, 2022): 1–10. http://dx.doi.org/10.1155/2022/5653942.

Full text

Abstract:

Deep learning is a branch of machine learning that uses neural networks to mimic the behaviour of the human brain. Various types of models are used in deep learning technology. This article will look at two important models and especially concentrate on unsupervised learning methodology. The two important models are as follows: the supervised and unsupervised models. The main difference is the method of training that they undergo. Supervised models are provided with training on a particular dataset and its outcome. In the case of unsupervised models, only input data is given, and there is no set outcome from which they can learn. The predicting/forecasting column is not present in an unsupervised model, unlike in the supervised model. Supervised models use regression to predict continuous quantities and classification to predict discrete class labels; unsupervised models use clustering to group similar models and association learning to find associations between items. Unsupervised migration is a combination of the unsupervised learning method and migration. In unsupervised learning, there is no need to supervise the models. Migration is an effective tool in processing and imaging data. Unsupervised learning allows the model to work independently to discover patterns and information that were previously undetected. It mainly works on unlabeled data. Unsupervised learning can achieve more complex processing tasks when compared to supervised learning. The unsupervised learning method is more unpredictable when compared with other types of learning methods. Some of the popular unsupervised learning algorithms include k-means clustering, hierarchal clustering, Apriori algorithm, clustering, anomaly detection, association mining, neural networks, etc. In this research article, we implement this particular deep learning model in the marketing oriented asset allocation of high level accounting talents. When the proposed unsupervised migration algorithm was compared to the existing Fractional Hausdorff Grey Model, it was discovered that the proposed system provided 99.12% accuracy by the high level accounting talented candidate in market-oriented asset allocation.

APA, Harvard, Vancouver, ISO, and other styles

26

Sadiq, Saad, Mei-Ling Shyu, and Daniel J. Feaster. "Counterfactual Autoencoder for Unsupervised Semantic Learning." International Journal of Multimedia Data Engineering and Management 9, no. 4 (October 2018): 1–20. http://dx.doi.org/10.4018/ijmdem.2018100101.

Full text

Abstract:

Deep Neural Networks (DNNs) are best known for being the state-of-the-art in artificial intelligence (AI) applications including natural language processing (NLP), speech processing, computer vision, etc. In spite of all recent achievements of deep learning, it has yet to achieve semantic learning required to reason about the data. This lack of reasoning is partially imputed to the boorish memorization of patterns and curves from millions of training samples and ignoring the spatiotemporal relationships. The proposed framework puts forward a novel approach based on variational autoencoders (VAEs) by using the potential outcomes model and developing the counterfactual autoencoders. The proposed framework transforms any sort of multimedia input distributions to a meaningful latent space while giving more control over how the latent space is created. This allows us to model data that is better suited to answer inference-based queries, which is very valuable in reasoning-based AI applications.

APA, Harvard, Vancouver, ISO, and other styles

27

Liu, Qiang, Haidong Zhang, Yiming Xu, and Li Wang. "Unsupervised Deep Learning-Based RGB-D Visual Odometry." Applied Sciences 10, no. 16 (August 6, 2020): 5426. http://dx.doi.org/10.3390/app10165426.

Full text

Abstract:

Recently, deep learning frameworks have been deployed in visual odometry systems and achieved comparable results to traditional feature matching based systems. However, most deep learning-based frameworks inevitably need labeled data as ground truth for training. On the other hand, monocular odometry systems are incapable of restoring absolute scale. External or prior information has to be introduced for scale recovery. To solve these problems, we present a novel deep learning-based RGB-D visual odometry system. Our two main contributions are: (i) during network training and pose estimation, the depth images are fed into the network to form a dual-stream structure with the RGB images, and a dual-stream deep neural network is proposed. (ii) the system adopts an unsupervised end-to-end training method, thus the labor-intensive data labeling task is not required. We have tested our system on the KITTI dataset, and results show that the proposed RGB-D Visual Odometry (VO) system has obvious advantages over other state-of-the-art systems in terms of both translation and rotation errors.

APA, Harvard, Vancouver, ISO, and other styles

28

Tan, Lu, Ling Li, Wan-Quan Liu, Sen-Jian An, and Kylie Munyard. "Unsupervised learning of multi-task deep variational model." Journal of Visual Communication and Image Representation 87 (August 2022): 103588. http://dx.doi.org/10.1016/j.jvcir.2022.103588.

Full text

APA, Harvard, Vancouver, ISO, and other styles

29

Droby, Ahmad, Berat Kurar Barakat, Raid Saabni, Reem Alaasam, Boraq Madi, and Jihad El-Sana. "Understanding Unsupervised Deep Learning for Text Line Segmentation." Applied Sciences 12, no. 19 (September 22, 2022): 9528. http://dx.doi.org/10.3390/app12199528.

Full text

Abstract:

We propose an unsupervised feature learning approach for segmenting text lines of handwritten document images with no labelling effort. Humans can easily group local text line features to global coarse patterns. We leverage this coherent visual perception of text lines as a supervising signal by formulating the feature learning as a global pattern differentiation task. The machine is trained to detect whether a document patch contains a similar global text line pattern with its identity or neighbours, and a different global text line pattern with its 90-degree-rotated identity or neighbours. Clustering the central windows of document image patches using their extracted features, forms blob lines which strike through the text lines. The blob lines guide an energy minimization function for extracting text lines in a binary image and guide a seam carving function for detecting baselines in a colour image. In identifying the aspect of the input patch that supports the actual prediction and clustering, we contribute toward the understanding of input patch functionality. We evaluate the method on several variants of text line segmentation datasets to demonstrate its effectiveness, visualize what it has learned, and enable it to comprehend its clustering strategy from a human perspective.

APA, Harvard, Vancouver, ISO, and other styles

30

A. Hosni Mahmoud, Hanan, Alaaeldin M. Hafez, and Eatedal Alabdulkreem. "Language-Independent Text Tokenization Using Unsupervised Deep Learning." Intelligent Automation & Soft Computing 35, no. 1 (2023): 321–34. http://dx.doi.org/10.32604/iasc.2023.026235.

Full text

APA, Harvard, Vancouver, ISO, and other styles

31

Yamawaki, Kazuhiro, Yongqing Sun, and Xian-Hua Han. "Blind Image Super Resolution Using Deep Unsupervised Learning." Electronics 10, no. 21 (October 23, 2021): 2591. http://dx.doi.org/10.3390/electronics10212591.

Full text

Abstract:

The goal of single image super resolution (SISR) is to recover a high-resolution (HR) image from a low-resolution (LR) image. Deep learning based methods have recently made a remarkable performance gain in terms of both the effectiveness and efficiency for SISR. Most existing methods have to be trained based on large-scale synthetic paired data in a fully supervised manner. With the available HR natural images, the corresponding LR images are usually synthesized with a simple fixed degradation operation, such as bicubic down-sampling. Then, the learned deep models with these training data usually face difficulty to be generalized to real scenarios with unknown and complicated degradation operations. This study exploits a novel blind image super-resolution framework using a deep unsupervised learning network. The proposed method can simultaneously predict the underlying HR image and its specific degradation operation from the observed LR image only without any prior knowledge. The experimental results on three benchmark datasets validate that our proposed method achieves a promising performance under the unknown degradation models.

APA, Harvard, Vancouver, ISO, and other styles

32

Khaldi, Yacine, Amir Benzaoui, Abdeldjalil Ouahabi, Sebastien Jacques, and Abdelmalik Taleb-Ahmed. "Ear Recognition Based on Deep Unsupervised Active Learning." IEEE Sensors Journal 21, no. 18 (September 15, 2021): 20704–13. http://dx.doi.org/10.1109/jsen.2021.3100151.

Full text

APA, Harvard, Vancouver, ISO, and other styles

33

Apostol, Ioana, Marius Preda, Constantin Nila, and Ion Bica. "IoT Botnet Anomaly Detection Using Unsupervised Deep Learning." Electronics 10, no. 16 (August 4, 2021): 1876. http://dx.doi.org/10.3390/electronics10161876.

Full text

Abstract:

The Internet of Things has become a cutting-edge technology that is continuously evolving in size, connectivity, and applicability. This ecosystem makes its presence felt in every aspect of our lives, along with all other emerging technologies. Unfortunately, despite the significant benefits brought by the IoT, the increased attack surface built upon it has become more critical than ever. Devices have limited resources and are not typically created with security features. Lately, a trend of botnet threats transitioning to the IoT environment has been observed, and an army of infected IoT devices can expand quickly and be used for effective attacks. Therefore, identifying proper solutions for securing IoT systems is currently an important and challenging research topic. Machine learning-based approaches are a promising alternative, allowing the identification of abnormal behaviors and the detection of attacks. This paper proposes an anomaly-based detection solution that uses unsupervised deep learning techniques to identify IoT botnet activities. An empirical evaluation of the proposed method is conducted on both balanced and unbalanced datasets to assess its threat detection capability. False-positive rate reduction and its impact on the detection system are also analyzed. Furthermore, a comparison with other unsupervised learning approaches is included. The experimental results reveal the performance of the proposed detection method.

APA, Harvard, Vancouver, ISO, and other styles

34

Patil, Kaveri R. "Language/Dialect Recognition based on Unsupervised Deep Learning." International Journal for Research in Applied Science and Engineering Technology 7, no. 6 (June 30, 2019): 2303–7. http://dx.doi.org/10.22214/ijraset.2019.6387.

Full text

APA, Harvard, Vancouver, ISO, and other styles

35

Zhang, Qian, and John H. L. Hansen. "Language/Dialect Recognition Based on Unsupervised Deep Learning." IEEE/ACM Transactions on Audio, Speech, and Language Processing 26, no. 5 (May 2018): 873–82. http://dx.doi.org/10.1109/taslp.2018.2797420.

Full text

APA, Harvard, Vancouver, ISO, and other styles

36

Yang, Xi, Kaizhu Huang, Rui Zhang, and John Y. Goulermas. "A Novel Deep Density Model for Unsupervised Learning." Cognitive Computation 11, no. 6 (June 25, 2018): 778–88. http://dx.doi.org/10.1007/s12559-018-9566-9.

Full text

APA, Harvard, Vancouver, ISO, and other styles

37

Krittanawong, Chayakrit, Anusith Tunhasiriwet, HongJu Zhang, Zhen Wang, Mehmet Aydar, and Takeshi Kitai. "Deep Learning With Unsupervised Feature in Echocardiographic Imaging." Journal of the American College of Cardiology 69, no. 16 (April 2017): 2100–2101. http://dx.doi.org/10.1016/j.jacc.2016.12.047.

Full text

APA, Harvard, Vancouver, ISO, and other styles

38

Shen, Yuming, Li Liu, and Ling Shao. "Unsupervised Binary Representation Learning with Deep Variational Networks." International Journal of Computer Vision 127, no. 11-12 (February 21, 2019): 1614–28. http://dx.doi.org/10.1007/s11263-019-01166-4.

Full text

APA, Harvard, Vancouver, ISO, and other styles

39

Solomon, Enoch, Abraham Woubie, and Krzysztof J. Cios. "UFace: An Unsupervised Deep Learning Face Verification System." Electronics 11, no. 23 (November 26, 2022): 3909. http://dx.doi.org/10.3390/electronics11233909.

Full text

Abstract:

Deep convolutional neural networks are often used for image verification but require large amounts of labeled training data, which are not always available. To address this problem, an unsupervised deep learning face verification system, called UFace, is proposed here. It starts by selecting from large unlabeled data the k most similar and k most dissimilar images to a given face image and uses them for training. UFace is implemented using methods of the autoencoder and Siamese network; the latter is used in all comparisons as its performance is better. Unlike in typical deep neural network training, UFace computes the loss function k times for similar images and k times for dissimilar images for each input image. UFace’s performance is evaluated using four benchmark face verification datasets: Labeled Faces in the Wild (LFW), YouTube Faces (YTF), Cross-age LFW (CALFW) and Celebrities in Frontal Profile in the Wild (CFP-FP). UFace with the Siamese network achieved accuracies of 99.40%, 96.04%, 95.12% and 97.89%, respectively, on the four datasets. These results are comparable with the state-of-the-art methods, such as ArcFace, GroupFace and MegaFace. The biggest advantage of UFace is that it uses much less training data and does not require labeled data.

APA, Harvard, Vancouver, ISO, and other styles

40

Károly, Artúr István, Róbert Fullér, and Péter Galambos. "Unsupervised Clustering for Deep Learning: A tutorial survey." Acta Polytechnica Hungarica 15, no. 8 (2018): 29–53. http://dx.doi.org/10.12700/aph.15.8.2018.8.2.

Full text

APA, Harvard, Vancouver, ISO, and other styles

41

Prashant Krishnan, V., S. Rajarajeswari, Venkat Krishnamohan, Vivek Chandra Sheel, and R. Deepak. "Music Generation Using Deep Learning Techniques." Journal of Computational and Theoretical Nanoscience 17, no. 9 (July 1, 2020): 3983–87. http://dx.doi.org/10.1166/jctn.2020.9003.

Full text

Abstract:

This paper primarily aims to compare two deep learning techniques in the task of learning musical styles and generating novel musical content. Long Short Term Memory (LSTM), a supervised learning algorithm is used, which is a variation of the Recurrent Neural Network (RNN), frequently used for sequential data. Another technique explored is Generative Adversarial Networks (GAN), an unsupervised approach which is used to learn a distribution of a particular style, and novelly combine components to create sequences. The representation of data from the MIDI files as chord and note embedding are essential to the performance of the models. This type of embedding in the network helps it to discover structural patterns in the samples. Through the study, it is seen how a supervised learning technique performs better than the unsupervised one. A study helped in obtaining a Mean Opinion Score (MOS), which was used as an indicator of the comparative quality and performance of the respective techniques.

APA, Harvard, Vancouver, ISO, and other styles

42

Hu, Xiang, Teng Li, Tong Zhou, Yu Liu, and Yuanxi Peng. "Contrastive Learning Based on Transformer for Hyperspectral Image Classification." Applied Sciences 11, no. 18 (September 17, 2021): 8670. http://dx.doi.org/10.3390/app11188670.

Full text

Abstract:

Recently, deep learning has achieved breakthroughs in hyperspectral image (HSI) classification. Deep-learning-based classifiers require a large number of labeled samples for training to provide excellent performance. However, the availability of labeled data is limited due to the significant human resources and time costs of labeling hyperspectral data. Unsupervised learning for hyperspectral image classification has thus received increasing attention. In this paper, we propose a novel unsupervised framework based on a contrastive learning method and a transformer model for hyperspectral image classification. The experimental results prove that our model can efficiently extract hyperspectral image features in unsupervised situations.

APA, Harvard, Vancouver, ISO, and other styles

43

Ferles, Christos, Yannis Papanikolaou, Stylianos P. Savaidis, and Stelios A. Mitilineos. "Deep Self-Organizing Map of Convolutional Layers for Clustering and Visualizing Image Data." Machine Learning and Knowledge Extraction 3, no. 4 (November 14, 2021): 879–99. http://dx.doi.org/10.3390/make3040044.

Full text

Abstract:

The self-organizing convolutional map (SOCOM) hybridizes convolutional neural networks, self-organizing maps, and gradient backpropagation optimization into a novel integrated unsupervised deep learning model. SOCOM structurally combines, architecturally stacks, and algorithmically fuses its deep/unsupervised learning components. The higher-level representations produced by its underlying convolutional deep architecture are embedded in its topologically ordered neural map output. The ensuing unsupervised clustering and visualization operations reflect the model’s degree of synergy between its building blocks and synopsize its range of applications. Clustering results are reported on the STL-10 benchmark dataset coupled with the devised neural map visualizations. The series of conducted experiments utilize a deep VGG-based SOCOM model.

APA, Harvard, Vancouver, ISO, and other styles

44

Ali, Afan, and Fan Yangyu. "Unsupervised feature learning and automatic modulation classification using deep learning model." Physical Communication 25 (December 2017): 75–84. http://dx.doi.org/10.1016/j.phycom.2017.09.004.

Full text

APA, Harvard, Vancouver, ISO, and other styles

45

Koohzadi, Maryam, Nasrollah Moghadam Charkari, and Foad Ghaderi. "Unsupervised representation learning based on the deep multi-view ensemble learning." Applied Intelligence 50, no. 2 (July 31, 2019): 562–81. http://dx.doi.org/10.1007/s10489-019-01526-0.

Full text

APA, Harvard, Vancouver, ISO, and other styles

46

Huang, Qiuyuan, Li Deng, Dapeng Wu, Chang Liu, and Xiaodong He. "Attentive Tensor Product Learning." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 1344–51. http://dx.doi.org/10.1609/aaai.v33i01.33011344.

Full text

Abstract:

This paper proposes a novel neural architecture — Attentive Tensor Product Learning (ATPL) — to represent grammatical structures of natural language in deep learning models. ATPL exploits Tensor Product Representations (TPR), a structured neural-symbolic model developed in cognitive science, to integrate deep learning with explicit natural language structures and rules. The key ideas of ATPL are: 1) unsupervised learning of role-unbinding vectors of words via the TPR-based deep neural network; 2) the use of attention modules to compute TPR; and 3) the integration of TPR with typical deep learning architectures including long short-term memory and feedforward neural networks. The novelty of our approach lies in its ability to extract the grammatical structure of a sentence by using role-unbinding vectors, which are obtained in an unsupervised manner. Our ATPL approach is applied to 1) image captioning, 2) part of speech (POS) tagging, and 3) constituency parsing of a natural language sentence. The experimental results demonstrate the effectiveness of the proposed approach in all these three natural language processing tasks.

APA, Harvard, Vancouver, ISO, and other styles

47

Längkvist, Martin, Lars Karlsson, and Amy Loutfi. "Sleep Stage Classification Using Unsupervised Feature Learning." Advances in Artificial Neural Systems 2012 (July 24, 2012): 1–9. http://dx.doi.org/10.1155/2012/107046.

Full text

Abstract:

Most attempts at training computers for the difficult and time-consuming task of sleep stage classification involve a feature extraction step. Due to the complexity of multimodal sleep data, the size of the feature space can grow to the extent that it is also necessary to include a feature selection step. In this paper, we propose the use of an unsupervised feature learning architecture called deep belief nets (DBNs) and show how to apply it to sleep data in order to eliminate the use of handmade features. Using a postprocessing step of hidden Markov model (HMM) to accurately capture sleep stage switching, we compare our results to a feature-based approach. A study of anomaly detection with the application to home environment data collection is also presented. The results using raw data with a deep architecture, such as the DBN, were comparable to a feature-based approach when validated on clinical datasets.

APA, Harvard, Vancouver, ISO, and other styles

48

Wang, Mou, Xiao-Lei Zhang, and Susanto Rahardja. "An Unsupervised Deep Learning System for Acoustic Scene Analysis." Applied Sciences 10, no. 6 (March 19, 2020): 2076. http://dx.doi.org/10.3390/app10062076.

Full text

Abstract:

Acoustic scene analysis has attracted a lot of attention recently. Existing methods are mostly supervised, which requires well-predefined acoustic scene categories and accurate labels. In practice, there exists a large amount of unlabeled audio data, but labeling large-scale data is not only costly but also time-consuming. Unsupervised acoustic scene analysis on the other hand does not require manual labeling but is known to have significantly lower performance and therefore has not been well explored. In this paper, a new unsupervised method based on deep auto-encoder networks and spectral clustering is proposed. It first extracts a bottleneck feature from the original acoustic feature of audio clips by an auto-encoder network, and then employs spectral clustering to further reduce the noise and unrelated information in the bottleneck feature. Finally, it conducts hierarchical clustering on the low-dimensional output of the spectral clustering. To fully utilize the spatial information of stereo audio, we further apply the binaural representation and conduct joint clustering on that. To the best of our knowledge, this is the first time that a binaural representation is being used in unsupervised learning. Experimental results show that the proposed method outperforms the state-of-the-art competing methods.

APA, Harvard, Vancouver, ISO, and other styles

49

Liu, Zhe, Yinqiang Zheng, and Xian-Hua Han. "Deep Unsupervised Fusion Learning for Hyperspectral Image Super Resolution." Sensors 21, no. 7 (March 28, 2021): 2348. http://dx.doi.org/10.3390/s21072348.

Full text

Abstract:

Hyperspectral image (HSI) super-resolution (SR) is a challenging task due to its ill-posed nature, and has attracted extensive attention by the research community. Previous methods concentrated on leveraging various hand-crafted image priors of a latent high-resolution hyperspectral (HR-HS) image to regularize the degradation model of the observed low-resolution hyperspectral (LR-HS) and HR-RGB images. Different optimization strategies for searching a plausible solution, which usually leads to a limited reconstruction performance, were also exploited. Recently, deep-learning-based methods evolved for automatically learning the abundant image priors in a latent HR-HS image. These methods have made great progress for HS image super resolution. Current deep-learning methods have faced difficulties in designing more complicated and deeper neural network architectures for boosting the performance. They also require large-scale training triplets, such as the LR-HS, HR-RGB, and their corresponding HR-HS images for neural network training. These training triplets significantly limit their applicability to real scenarios. In this work, a deep unsupervised fusion-learning framework for generating a latent HR-HS image using only the observed LR-HS and HR-RGB images without previous preparation of any other training triplets is proposed. Based on the fact that a convolutional neural network architecture is capable of capturing a large number of low-level statistics (priors) of images, the automatic learning of underlying priors of spatial structures and spectral attributes in a latent HR-HS image using only its corresponding degraded observations is promoted. Specifically, the parameter space of a generative neural network used for learning the required HR-HS image to minimize the reconstruction errors of the observations using mathematical relations between data is investigated. Moreover, special convolutional layers for approximating the degradation operations between observations and the latent HR-HS image are specifically to construct an end-to-end unsupervised learning framework for HS image super-resolution. Experiments on two benchmark HS datasets, including the CAVE and Harvard, demonstrate that the proposed method can is capable of producing very promising results, even under a large upscaling factor. Furthermore, it can outperform other unsupervised state-of-the-art methods by a large margin, and manifests its superiority and efficiency.

APA, Harvard, Vancouver, ISO, and other styles

50

Brattoli, Biagio, Uta Büchler, Michael Dorkenwald, Philipp Reiser, Linard Filli, Fritjof Helmchen, Anna-Sophia Wahl, and Björn Ommer. "Unsupervised behaviour analysis and magnification (uBAM) using deep learning." Nature Machine Intelligence 3, no. 6 (April 5, 2021): 495–506. http://dx.doi.org/10.1038/s42256-021-00326-x.

Full text

APA, Harvard, Vancouver, ISO, and other styles

Journal articles on the topic 'Deep Unsupervised Learning'

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles