Journal articles on the topic 'Noisy-OR model'
To see the other types of publications on this topic, follow the link: Noisy-OR model.
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 'Noisy-OR model.'
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
Quintanar-Gago, David A., and Pamela F. Nelson. "The extended Recursive Noisy OR model: Static and dynamic considerations." International Journal of Approximate Reasoning 139 (December 2021): 185–200. http://dx.doi.org/10.1016/j.ijar.2021.09.013.
Full text
2
Zhou, Kuang, Arnaud Martin, and Quan Pan. "The Belief Noisy-OR Model Applied to Network Reliability Analysis." International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems 24, no. 06 (November 30, 2016): 937–60. http://dx.doi.org/10.1142/s0218488516500434.
Full textAbstract:
One difficulty faced in knowledge engineering for Bayesian Network (BN) is the quantification step where the Conditional Probability Tables (CPTs) are determined. The number of parameters included in CPTs increases exponentially with the number of parent variables. The most common solution is the application of the so-called canonical gates. The Noisy-OR (NOR) gate, which takes advantage of the independence of causal interactions, provides a logarithmic reduction of the number of parameters required to specify a CPT. In this paper, an extension of NOR model based on the theory of belief functions, named Belief Noisy-OR (BNOR), is proposed. BNOR is capable of dealing with both aleatory and epistemic uncertainty of the network. Compared with NOR, more rich information which is of great value for making decisions can be got when the available knowledge is uncertain. Specially, when there is no epistemic uncertainty, BNOR degrades into NOR. Additionally, different structures of BNOR are presented in this paper in order to meet various needs of engineers. The application of BNOR model on the reliability evaluation problem of networked systems demonstrates its effectiveness.
3
Li, W., P. Poupart, and P. Van Beek. "Exploiting Structure in Weighted Model Counting Approaches to Probabilistic Inference." Journal of Artificial Intelligence Research 40 (April 19, 2011): 729–65. http://dx.doi.org/10.1613/jair.3232.
Full textAbstract:
Previous studies have demonstrated that encoding a Bayesian network into a SAT formula and then performing weighted model counting using a backtracking search algorithm can be an effective method for exact inference. In this paper, we present techniques for improving this approach for Bayesian networks with noisy-OR and noisy-MAX relations---two relations that are widely used in practice as they can dramatically reduce the number of probabilities one needs to specify. In particular, we present two SAT encodings for noisy-OR and two encodings for noisy-MAX that exploit the structure or semantics of the relations to improve both time and space efficiency, and we prove the correctness of the encodings. We experimentally evaluated our techniques on large-scale real and randomly generated Bayesian networks. On these benchmarks, our techniques gave speedups of up to two orders of magnitude over the best previous approaches for networks with noisy-OR/MAX relations and scaled up to larger networks. As well, our techniques extend the weighted model counting approach for exact inference to networks that were previously intractable for the approach.
4
Büttner, Martha, Lisa Schneider, Aleksander Krasowski, Joachim Krois, Ben Feldberg, and Falk Schwendicke. "Impact of Noisy Labels on Dental Deep Learning—Calculus Detection on Bitewing Radiographs." Journal of Clinical Medicine 12, no. 9 (April 23, 2023): 3058. http://dx.doi.org/10.3390/jcm12093058.
Full textAbstract:
Supervised deep learning requires labelled data. On medical images, data is often labelled inconsistently (e.g., too large) with varying accuracies. We aimed to assess the impact of such label noise on dental calculus detection on bitewing radiographs. On 2584 bitewings calculus was accurately labeled using bounding boxes (BBs) and artificially increased and decreased stepwise, resulting in 30 consistently and 9 inconsistently noisy datasets. An object detection network (YOLOv5) was trained on each dataset and evaluated on noisy and accurate test data. Training on accurately labeled data yielded an mAP50: 0.77 (SD: 0.01). When trained on consistently too small BBs model performance significantly decreased on accurate and noisy test data. Model performance trained on consistently too large BBs decreased immediately on accurate test data (e.g., 200% BBs: mAP50: 0.24; SD: 0.05; p < 0.05), but only after drastically increasing BBs on noisy test data (e.g., 70,000%: mAP50: 0.75; SD: 0.01; p < 0.05). Models trained on inconsistent BB sizes showed a significant decrease of performance when deviating 20% or more from the original when tested on noisy data (mAP50: 0.74; SD: 0.02; p < 0.05), or 30% or more when tested on accurate data (mAP50: 0.76; SD: 0.01; p < 0.05). In conclusion, accurate predictions need accurate labeled data in the training process. Testing on noisy data may disguise the effects of noisy training data. Researchers should be aware of the relevance of accurately annotated data, especially when testing model performances.
5
Shang, Yuming, He-Yan Huang, Xian-Ling Mao, Xin Sun, and Wei Wei. "Are Noisy Sentences Useless for Distant Supervised Relation Extraction?" Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 05 (April 3, 2020): 8799–806. http://dx.doi.org/10.1609/aaai.v34i05.6407.
Full textAbstract:
The noisy labeling problem has been one of the major obstacles for distant supervised relation extraction. Existing approaches usually consider that the noisy sentences are useless and will harm the model's performance. Therefore, they mainly alleviate this problem by reducing the influence of noisy sentences, such as applying bag-level selective attention or removing noisy sentences from sentence-bags. However, the underlying cause of the noisy labeling problem is not the lack of useful information, but the missing relation labels. Intuitively, if we can allocate credible labels for noisy sentences, they will be transformed into useful training data and benefit the model's performance. Thus, in this paper, we propose a novel method for distant supervised relation extraction, which employs unsupervised deep clustering to generate reliable labels for noisy sentences. Specifically, our model contains three modules: a sentence encoder, a noise detector and a label generator. The sentence encoder is used to obtain feature representations. The noise detector detects noisy sentences from sentence-bags, and the label generator produces high-confidence relation labels for noisy sentences. Extensive experimental results demonstrate that our model outperforms the state-of-the-art baselines on a popular benchmark dataset, and can indeed alleviate the noisy labeling problem.
6
Zheng, Guoqing, Ahmed Hassan Awadallah, and Susan Dumais. "Meta Label Correction for Noisy Label Learning." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 12 (May 18, 2021): 11053–61. http://dx.doi.org/10.1609/aaai.v35i12.17319.
Full textAbstract:
Leveraging weak or noisy supervision for building effective machine learning models has long been an important research problem. Its importance has further increased recently due to the growing need for large-scale datasets to train deep learning models. Weak or noisy supervision could originate from multiple sources including non-expert annotators or automatic labeling based on heuristics or user interaction signals. There is an extensive amount of previous work focusing on leveraging noisy labels. Most notably, recent work has shown impressive gains by using a meta-learned instance re-weighting approach where a meta-learning framework is used to assign instance weights to noisy labels. In this paper, we extend this approach via posing the problem as a label correction problem within a meta-learning framework. We view the label correction procedure as a meta-process and propose a new meta-learning based framework termed MLC (Meta Label Correction) for learning with noisy labels. Specifically, a label correction network is adopted as a meta-model to produce corrected labels for noisy labels while the main model is trained to leverage the corrected labels. Both models are jointly trained by solving a bi-level optimization problem. We run extensive experiments with different label noise levels and types on both image recognition and text classification tasks. We compare the re-weighing and correction approaches showing that the correction framing addresses some of the limitations of re-weighting. We also show that the proposed MLC approach outperforms previous methods in both image and language tasks.
7
Maeda, Shin-ichi, Wen-Jie Song, and Shin Ishii. "Nonlinear and Noisy Extension of Independent Component Analysis: Theory and Its Application to a Pitch Sensation Model." Neural Computation 17, no. 1 (January 1, 2005): 115–44. http://dx.doi.org/10.1162/0899766052530866.
Full textAbstract:
In this letter, we propose a noisy nonlinear version of independent component analysis (ICA). Assuming that the probability density function (p.d.f.) of sources is known, a learning rule is derived based on maximum likelihood estimation (MLE). Our model involves some algorithms of noisy linear ICA (e.g., Bermond & Cardoso, 1999) or noise-free nonlinear ICA (e.g., Lee, Koehler, & Orglmeister, 1997) as special cases. Especially when the nonlinear function is linear, the learning rule derived as a generalized expectation-maximization algorithm has a similar form to the noisy ICA algorithm previously presented by Douglas, Cichocki, and Amari (1998). Moreover, our learning rule becomes identical to the standard noise-free linear ICA algorithm in the noiseless limit, while existing MLE-based noisy ICA algorithms do not rigorously include the noise-free ICA. We trained our noisy nonlinear ICA by using acoustic signals such as speech and music. The model after learning successfully simulates virtual pitch phenomena, and the existence region of virtual pitch is qualitatively similar to that observed in a psychoacoustic experiment. Although a linear transformation hypothesized in the central auditory system can account for the pitch sensation, our model suggests that the linear transformation can be acquired through learning from actual acoustic signals. Since our model includes a cepstrum analysis in a special case, it is expected to provide a useful feature extraction method that has often been given by the cepstrum analysis.
8
Zhan, Peida, Hong Jiao, Kaiwen Man, and Lijun Wang. "Using JAGS for Bayesian Cognitive Diagnosis Modeling: A Tutorial." Journal of Educational and Behavioral Statistics 44, no. 4 (February 10, 2019): 473–503. http://dx.doi.org/10.3102/1076998619826040.
Full textAbstract:
In this article, we systematically introduce the just another Gibbs sampler (JAGS) software program to fit common Bayesian cognitive diagnosis models (CDMs) including the deterministic inputs, noisy “and” gate model; the deterministic inputs, noisy “or” gate model; the linear logistic model; the reduced reparameterized unified model; and the log-linear CDM (LCDM). Further, we introduce the unstructured latent structural model and the higher order latent structural model. We also show how to extend these models to consider polytomous attributes, the testlet effect, and longitudinal diagnosis. Finally, we present an empirical example as a tutorial to illustrate how to use JAGS codes in R.
9
Hong, Zhiwei, Xiaocheng Fan, Tao Jiang, and Jianxing Feng. "End-to-End Unpaired Image Denoising with Conditional Adversarial Networks." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (April 3, 2020): 4140–49. http://dx.doi.org/10.1609/aaai.v34i04.5834.
Full textAbstract:
Image denoising is a classic low level vision problem that attempts to recover a noise-free image from a noisy observation. Recent advances in deep neural networks have outperformed traditional prior based methods for image denoising. However, the existing methods either require paired noisy and clean images for training or impose certain assumptions on the noise distribution and data types. In this paper, we present an end-to-end unpaired image denoising framework (UIDNet) that denoises images with only unpaired clean and noisy training images. The critical component of our model is a noise learning module based on a conditional Generative Adversarial Network (cGAN). The model learns the noise distribution from the input noisy images and uses it to transform the input clean images to noisy ones without any assumption on the noise distribution and data types. This process results in pairs of clean and pseudo-noisy images. Such pairs are then used to train another denoising network similar to the existing denoising methods based on paired images. The noise learning and denoising components are integrated together so that they can be trained end-to-end. Extensive experimental evaluation has been performed on both synthetic and real data including real photographs and computer tomography (CT) images. The results demonstrate that our model outperforms the previous models trained on unpaired images as well as the state-of-the-art methods based on paired training data when proper training pairs are unavailable.
10
Kağan Akkaya, Emre, and Burcu Can. "Transfer learning for Turkish named entity recognition on noisy text." Natural Language Engineering 27, no. 1 (January 28, 2020): 35–64. http://dx.doi.org/10.1017/s1351324919000627.
Full textAbstract:
AbstractIn this article, we investigate using deep neural networks with different word representation techniques for named entity recognition (NER) on Turkish noisy text. We argue that valuable latent features for NER can, in fact, be learned without using any hand-crafted features and/or domain-specific resources such as gazetteers and lexicons. In this regard, we utilize character-level, character n-gram-level, morpheme-level, and orthographic character-level word representations. Since noisy data with NER annotation are scarce for Turkish, we introduce a transfer learning model in order to learn infrequent entity types as an extension to the Bi-LSTM-CRF architecture by incorporating an additional conditional random field (CRF) layer that is trained on a larger (but formal) text and a noisy text simultaneously. This allows us to learn from both formal and informal/noisy text, thus improving the performance of our model further for rarely seen entity types. We experimented on Turkish as a morphologically rich language and English as a relatively morphologically poor language. We obtained an entity-level F1 score of 67.39% on Turkish noisy data and 45.30% on English noisy data, which outperforms the current state-of-art models on noisy text. The English scores are lower compared to Turkish scores because of the intense sparsity in the data introduced by the user writing styles. The results prove that using subword information significantly contributes to learning latent features for morphologically rich languages.
11
Jittawiriyanukoon, Chanintorn. "Estimation of regression-based model with bulk noisy data." International Journal of Electrical and Computer Engineering (IJECE) 9, no. 5 (October 1, 2019): 3649. http://dx.doi.org/10.11591/ijece.v9i5.pp3649-3656.
Full textAbstract:
<span>The bulk noise has been provoking a contributed data due to a communication network with a tremendously low signal to noise ratio. An appreciated method for revising massive noise of individuals through information theory is widely discussed. One of the practical applications of this approach for bulk noise estimation is analyzed using intelligent automation and machine learning tools, dealing the case of bulk noise existence or nonexistence. A regression-based model is employed for the investigation and experiment. Estimation for the practical case with bulk noisy datasets is proposed. The proposed method applies slice-and-dice technique to partition a body of datasets down into slighter portions so that it can be carried out. The average error, correlation, absolute error and mean square error are computed to validate the estimation. Results from massive online analysis will be verified with data collected in the following period. In many cases, the prediction with bulk noisy data through MOA simulation reveals Random Imputation minimizes the average error.</span>
12
Hanafusa, Ryo, and Takeshi Okadome. "Bayesian Kernel Regression for Noisy Inputs Based on Nadaraya–Watson Estimator Constructed from Noiseless Training Data." Advances in Data Science and Adaptive Analysis 12, no. 01 (January 2020): 2050004. http://dx.doi.org/10.1142/s2424922x20500047.
Full textAbstract:
In regression for noisy inputs, noise is typically removed from a given noisy input if possible, and then the resulting noise-free input is provided to the regression function. In some cases, however, there is no available time or method for removing noise. The regression method proposed in this paper determines a regression function for noisy inputs using the estimated posterior of their noise-free constituents with a nonparametric estimator for noiseless explanatory values, which is constructed from noiseless training data. In addition, a probabilistic generative model is presented for estimating the noise distribution. This enables us to determine the noise distribution parametrically from a single noisy input, using the distribution of the noise-free constituent of noisy input estimated from the training data set as a prior. Experiments conducted using artificial and real data sets show that the proposed method suppresses the overfitting of the regression function for noisy inputs and the root mean squared errors (RMSEs) of the predictions are smaller compared with those of an existing method.
13
Bhagawati, Rupam, and Thiruselvan Subramanian. "Quantum-aided feature selection model – A quantum machine learning approach." Journal of Discrete Mathematical Sciences & Cryptography 26, no. 3 (2023): 641–55. http://dx.doi.org/10.47974/jdmsc-1735.
Full textAbstract:
The accuracy of information retrieval systems is measured by the relevancy of retrieved results as per the user’s query. Relevant results are presented by performing various methods viz. indexing and crawling and the output of these processes is the retrieved results that have to pass through the ranking process which is the central goal of information retrieval systems. The ranking is carried out through the classification or clustering of processed results which can include redundant and noisy features. The accuracy of classification or clusters for the ranking process can be maximized by removing noisy and duplicate features through the feature selection method. Although feature selection is an expensive computational process, after many decades, quantum computation tools are in use for many algorithms to implement realistic problems, particularly in the standard of Quantum Annealing. This paper focuses to prospect the standard of quantum computing in order to increase the quality of information classes through the feature selection method. The persuasiveness of the quantum approach is comparable to the classical process that focused on the reliability of quantum methodology from different perspectives.
14
Surin, V. A. "ON PROCESSING NOISY CONTRAST IMAGES." Bulletin of the South Ural State University series "Mathematics. Mechanics. Physics" 13, no. 1 (2021): 14–21. http://dx.doi.org/10.14529/mmph210102.
Full textAbstract:
The problem of noise reduction at sharp transitions of brightness in digital noisy contrast images is considered. In addition to the useful signal, digital images obtained by digitizing an analogue signal with a digital photo matrix have a noise component. Moreover, to obtain a digital image in the standard RGB color model, a demosaicing interpolation algorithm must be applied to the image obtained from a digital photo matrix. Due to such transformations, the Gaussian distribution of noise in a digital noisy image is violated. Using a standard image digitization model for noise reduction is not effective. For more effective noise reduction, the digital image is transferred from the RGB color model to the HSV or LAB color model, where the brightness and color components of the digital noise can be filtered separately. Color noise is suppressed in the color channels of the image using a Gaussian filter. Noise reduction in the brightness channel of a digital image is more difficult task, especially at the edge of sharp transitions of brightness. To suppress the brightness noise in contrast images, it is proposed to use a nonlinear filter based on the generalized method of least absolute values (GMLAV). The process of smoothing the contrast noisy transition by the GMLAV-filter is described, and its efficiency is shown in comparison with the median filtration.
15
Hossain, Md Nahid, Samiul Basir, Md Shakhawat Hosen, A. O. M. Asaduzzaman, Md Mojahidul Islam, Mohammad Alamgir Hossain, and Md Shohidul Islam. "Supervised Single Channel Speech Enhancement Method Using UNET." Electronics 12, no. 14 (July 12, 2023): 3052. http://dx.doi.org/10.3390/electronics12143052.
Full textAbstract:
This paper proposes an innovative single-channel supervised speech enhancement (SE) method based on UNET, a convolutional neural network (CNN) architecture that expands on a few changes in the basic CNN architecture. In the training phase, short-time Fourier transform (STFT) is exploited on the noisy time domain signal to build a noisy time-frequency domain signal which is called a complex noisy matrix. We take the real and imaginary parts of the complex noisy matrix and concatenate both of them to form the noisy concatenated matrix. We apply UNET to the noisy concatenated matrix for extracting speech components and train the CNN model. In the testing phase, the same procedure is applied to the noisy time-domain signal as in the training phase in order to construct another noisy concatenated matrix that can be tested using a pre-trained or saved model in order to construct an enhanced concatenated matrix. Finally, from the enhanced concatenated matrix, we separate both the imaginary and real parts to form an enhanced complex matrix. Magnitude and phase are then extracted from the newly created enhanced complex matrix. By using that magnitude and phase, the inverse STFT (ISTFT) can generate the enhanced speech signal. Utilizing the IEEE databases and various types of noise, including stationary and non-stationary noise, the proposed method is evaluated. Comparing the exploratory results of the proposed algorithm to the other five methods of STFT, sparse non-negative matrix factorization (SNMF), dual-tree complex wavelet transform (DTCWT)-SNMF, DTCWT-STFT-SNMF, STFT-convolutional denoising auto encoder (CDAE) and casual multi-head attention mechanism (CMAM) for speech enhancement, we determine that the proposed algorithm generally improves speech quality and intelligibility at all considered signal-to-noise ratios (SNRs). The suggested approach performs better than the other five competing algorithms in every evaluation metric.
16
Liu, Kun-Lin, Wu-Jun Li, and Minyi Guo. "Emoticon Smoothed Language Models for Twitter Sentiment Analysis." Proceedings of the AAAI Conference on Artificial Intelligence 26, no. 1 (September 20, 2021): 1678–84. http://dx.doi.org/10.1609/aaai.v26i1.8353.
Full textAbstract:
Twitter sentiment analysis (TSA) has become a hot research topic in recent years. The goal of this task is to discover the attitude or opinion of the tweets, which is typically formulated as a machine learning based text classification problem. Some methods use manually labeled data to train fully supervised models, while others use some noisy labels, such as emoticons and hashtags, for model training. In general, we can only get a limited number of training data for the fully supervised models because it is very labor-intensive and time-consuming to manually label the tweets. As for the models with noisy labels, it is hard for them to achieve satisfactory performance due to the noise in the labels although it is easy to get a large amount of data for training. Hence, the best strategy is to utilize both manually labeled data and noisy labeled data for training. However, how to seamlessly integrate these two different kinds of data into the same learning framework is still a challenge. In this paper, we present a novel model, called emoticon smoothed language model (ESLAM), to handle this challenge. The basic idea is to train a language model based on the manually labeled data, and then use the noisy emoticon data for smoothing. Experiments on real data sets demonstrate that ESLAM can effectively integrate both kinds of data to outperform those methods using only one of them.
17
Kourehli, Seyed Sina. "Damage Assessment in Structures Using Incomplete Modal Data and Artificial Neural Network." International Journal of Structural Stability and Dynamics 15, no. 06 (June 17, 2015): 1450087. http://dx.doi.org/10.1142/s0219455414500874.
Full textAbstract:
This paper presents a novel approach for structural damage detection and estimation using incomplete noisy modal data and artificial neural network (ANN). A feed-forward back propagation network is proposed for estimating the structural damage location and severity. Incomplete modal data is used in the dynamic analysis of damaged structures by the condensed finite element model and as input parameters to the neural network for damage identification. In all cases, the first two natural modes were used for the training process. The present method is applied to three examples consisting of a simply supported beam, three-story plane frame, and spring-mass system. Also, the effect of the discrepancy in mass and stiffness between the finite element model and the actual tested dynamic system has been investigated. The results demonstrated the accuracy and efficiency of the proposed method using incomplete modal data, which may be noisy or noise-free.
18
Lindner, John F., Brian K. Meadows, Tracey L. Marsh, William L. Ditto, and Adi R. Bulsara. "Can Neurons Distinguish Chaos from Noise?" International Journal of Bifurcation and Chaos 08, no. 04 (April 1998): 767–81. http://dx.doi.org/10.1142/s0218127498000565.
Full textAbstract:
Recent studies suggesting evidence for determinism in the stochastic activity of the heart and brain have sparked an important scientific debate: Do biological systems exploit chaos or are they merely noisy? Here, we analyze the spike interval statistics of a simple integrate-and-fire model neuron to investigate how a real neuron might process noise and chaos, and possibly differentiate between the two. In some cases, our model neuron readily distinguishes noise from chaos, even discriminating among chaos characterized by different Lyapunov exponents. However, in other cases, the model neuron does not decisively differentiate noise from chaos. In these cases, the spectral content of the input signal may be more significant than its phase space structure, and higher-order spectral characterizations may be necessary to distinguish its response to chaotic or noisy inputs.
19
Guan, Qingji, Qinrun Chen, and Yaping Huang. "An Improved Heteroscedastic Modeling Method for Chest X-ray Image Classification with Noisy Labels." Algorithms 16, no. 5 (May 4, 2023): 239. http://dx.doi.org/10.3390/a16050239.
Full textAbstract:
Chest X-ray image classification suffers from the high inter-similarity in appearance that is vulnerable to noisy labels. The data-dependent and heteroscedastic characteristic label noise make chest X-ray image classification more challenging. To address this problem, in this paper, we first revisit the heteroscedastic modeling (HM) for image classification with noise labels. Rather than modeling all images in one fell swoop as in HM, we instead propose a novel framework that considers the noisy and clean samples separately for chest X-ray image classification. The proposed framework consists of a Gaussian Mixture Model-based noise detector and a Heteroscedastic Modeling-based noise-aware classification network, named GMM-HM. The noise detector is constructed to judge whether one sample is clean or noisy. The noise-aware classification network models the noisy and clean samples with heteroscedastic and homoscedastic hypotheses, respectively. Through building the correlations between the corrupted noisy samples, the GMM-HM is much more robust than HM, which uses only the homoscedastic hypothesis. Compared with HM, we show consistent improvements on the ChestX-ray2017 dataset with different levels of symmetric and asymmetric noise. Furthermore, we also conduct experiments on a real asymmetric noisy dataset, ChestX-ray14. The experimental results on ChestX-ray14 show the superiority of the proposed method.
20
Wei, Penghui, Wenji Mao, and Guandan Chen. "A Topic-Aware Reinforced Model for Weakly Supervised Stance Detection." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 7249–56. http://dx.doi.org/10.1609/aaai.v33i01.33017249.
Full textAbstract:
Analyzing public attitudes plays an important role in opinion mining systems. Stance detection aims to determine from a text whether its author is in favor of, against, or neutral towards a given target. One challenge of this task is that a text may not explicitly express an attitude towards the target, but existing approaches utilize target content alone to build models. Moreover, although weakly supervised approaches have been proposed to ease the burden of manually annotating largescale training data, such approaches are confronted with noisy labeling problem. To address the above two issues, in this paper, we propose a Topic-Aware Reinforced Model (TARM) for weakly supervised stance detection. Our model consists of two complementary components: (1) a detection network that incorporates target-related topic information into representation learning for identifying stance effectively; (2) a policy network that learns to eliminate noisy instances from auto-labeled data based on off-policy reinforcement learning. Two networks are alternately optimized to improve each other’s performances. Experimental results demonstrate that our proposed model TARM outperforms the state-of-the-art approaches.
21
Kittisuwan, Pichid. "Low-complexity image denoising based on mixture model and simple form of MMSE estimation." International Journal of Wavelets, Multiresolution and Information Processing 16, no. 06 (October 10, 2018): 1850052. http://dx.doi.org/10.1142/s0219691318500522.
Full textAbstract:
In order to enhance efficiency of artificial intelligence (AI) tools such as classification or pattern recognition, it is important to have noise-free data to be processed with AI tools. Therefore, the study of algorithms used for reducing noise is also very significant. In thermal condition, Gaussian noise is important problem in analog circuit and image processing. Therefore, this paper focuses on the study of an algorithm for Gaussian noise reduction. In recent year, Bayesian with wavelet-based methods provides good efficiency in noise reduction and spends short time in processing. In Bayesian method, mixture density is more flexible than non-mixture density. Therefore, we proposed novel form of minimum mean square error (MMSE) estimation for mixture model, Pearson type VII and logistic densities, in Gaussian noise. The expectation-maximization (EM) algorithm is most deeply used for computing statistical parameters of mixture model. However, the EM estimator for the proposed method does not have the closed-form. Numerical methods are required to implement an EM algorithm. Therefore, we employ maximum a posteriori (MAP) estimation to compute local noisy variances with half-normal distribution prior for local noisy variances and Gaussian density for noisy wavelet coefficients. Here, the proposed method is expressed in closed-form. The denoising results present that our proposed algorithm outperforms the state-of-the-art method qualitatively and quantitatively.
22
Mendonça, J. Ricardo G. "The inactive–active phase transition in the noisy additive (exclusive-or) probabilistic cellular automaton." International Journal of Modern Physics C 27, no. 02 (December 23, 2015): 1650016. http://dx.doi.org/10.1142/s0129183116500169.
Full textAbstract:
We investigate the inactive–active phase transition in an array of additive (exclusive-or) cellular automata (CA) under noise. The model is closely related with the Domany-Kinzel (DK) probabilistic cellular automaton (PCA), for which there are rigorous as well as numerical estimates on the transition probabilities. Here, we characterize the critical behavior of the noisy additive cellular automaton by mean field analysis and finite-size scaling and show that its phase transition belongs to the directed percolation universality class of critical behavior. As a by-product of our analysis, we argue that the critical behavior of the noisy elementary CA 90 and 102 (in Wolfram’s enumeration scheme) must be the same. We also perform an empirical investigation of the mean field equations to assess their quality and find that away from the critical point (but not necessarily very far away) the mean field approximations provide a reasonably good description of the dynamics of the PCA.
23
Mousavi, Hamid, Mareike Buhl, Enrico Guiraud, Jakob Drefs, and Jörg Lücke. "Inference and Learning in a Latent Variable Model for Beta Distributed Interval Data." Entropy 23, no. 5 (April 29, 2021): 552. http://dx.doi.org/10.3390/e23050552.
Full textAbstract:
Latent Variable Models (LVMs) are well established tools to accomplish a range of different data processing tasks. Applications exploit the ability of LVMs to identify latent data structure in order to improve data (e.g., through denoising) or to estimate the relation between latent causes and measurements in medical data. In the latter case, LVMs in the form of noisy-OR Bayes nets represent the standard approach to relate binary latents (which represent diseases) to binary observables (which represent symptoms). Bayes nets with binary representation for symptoms may be perceived as a coarse approximation, however. In practice, real disease symptoms can range from absent over mild and intermediate to very severe. Therefore, using diseases/symptoms relations as motivation, we here ask how standard noisy-OR Bayes nets can be generalized to incorporate continuous observables, e.g., variables that model symptom severity in an interval from healthy to pathological. This transition from binary to interval data poses a number of challenges including a transition from a Bernoulli to a Beta distribution to model symptom statistics. While noisy-OR-like approaches are constrained to model how causes determine the observables’ mean values, the use of Beta distributions additionally provides (and also requires) that the causes determine the observables’ variances. To meet the challenges emerging when generalizing from Bernoulli to Beta distributed observables, we investigate a novel LVM that uses a maximum non-linearity to model how the latents determine means and variances of the observables. Given the model and the goal of likelihood maximization, we then leverage recent theoretical results to derive an Expectation Maximization (EM) algorithm for the suggested LVM. We further show how variational EM can be used to efficiently scale the approach to large networks. Experimental results finally illustrate the efficacy of the proposed model using both synthetic and real data sets. Importantly, we show that the model produces reliable results in estimating causes using proofs of concepts and first tests based on real medical data and on images.
24
PARK, HYUNG-MIN, JONG-HWAN LEE, TAESU KIM, UN-MIN BAE, BYUNG TAEK KIM, KI-YOUNG PARK, CHANG-MIN KIM, and SOO-YOUNG LEE. "MODELING AUDITORY PATHWAY FOR INTELLIGENT INFORMATION ACQUISITION." International Journal of Information Acquisition 01, no. 04 (December 2004): 345–56. http://dx.doi.org/10.1142/s0219878904000367.
Full textAbstract:
An auditory model has been developed for an intelligent speech information acquisition system in real-world noisy environment. The developed mathematical model of the human auditory pathway consists of three components, i.e. the nonlinear feature extraction from cochlea to auditory cortex, the binaural processing at superior olivery complex, and the top-down attention from higher brain to the cochlea. The feature extraction is based on information-theoretic sparse coding throughout the auditory pathway. Also, the time-frequency masking is incorporated as a model of the lateral inhibition in both time and frequency domain. The binaural processing is modeled as the blind signal separation and adaptive noise canceling based on the independent component analysis with hundreds of time-delays for noisy reverberated signals. The Top-Down (TD) attention comes from familiarity and/or importance of the sensory information, i.e. the sound, and a simple but efficient TD attention model had been developed based on the error backpropagation algorithm. Also, the binaural processing and top-down attention are combined for speech signals with heavy noises. This auditory model requires extensive computing, and special hardware had been developed for real-time applications. Experimental results demonstrate much better recognition performance in real-world noisy environments.
25
Fawwaz, Dzaky Zakiyal, and Sang-Hwa Chung. "Real-Time and Robust Hydraulic System Fault Detection via Edge Computing." Applied Sciences 10, no. 17 (August 27, 2020): 5933. http://dx.doi.org/10.3390/app10175933.
Full textAbstract:
We consider fault detection in a hydraulic system that maintains multivariate time-series sensor data. Such a real-world industrial environment could suffer from noisy data resulting from inaccuracies in hardware sensing or external interference. Thus, we propose a real-time and robust fault detection method for hydraulic systems that leverages cooperation between cloud and edge servers. The cloud server employs a new approach that includes a genetic algorithm (GA)-based feature selection that identifies feature-to-label correlations and feature-to-feature redundancies. A GA can efficiently process large search spaces, such as solving a combinatorial optimization problem to identify the optimal feature subset. By using fewer important features that require transmission and processing, this approach reduces detection time and improves model performance. We propose a long short-term memory autoencoder for a robust fault detection model that leverages temporal information on time-series sensor data and effectively handles noisy data. This detection model is then deployed at edge servers that provide computing resources near the data source to reduce latency. Our experimental results suggest that this method outperforms prior approaches by demonstrating lower detection times, higher accuracy, and increased robustness to noisy data. While we have a 63% reduction of features, our model obtains a high accuracy of approximately 98% and is robust to noisy data with a signal-to-noise ratio near 0 dB. Our method also performs at an average detection time of only 9.42 ms with a reduced average packet size of 179.98 KB from the maximum of 343.78 KB.
26
Wang, Xiao Fei, Bo Nian Li, Yan Li Huang, and Xin Ran Wang. "Feature Extraction from Noisy Image Using Intersecting Cortical Model." Applied Mechanics and Materials 40-41 (November 2010): 516–22. http://dx.doi.org/10.4028/www.scientific.net/amm.40-41.516.
Full textAbstract:
This paper introduces an efficient approach for feature extraction from noisy image using Intersecting Cortical Model(ICM), which is a simplified model of Pulse-Coupled Neural Network(PCNN). In our research, the entropy sequence of the output image, is obtained from the original gray image by ICM, as feature vector of the gray image, which can be used to represent the gray image, and this has been proved by our experiments. Consequently, it is used in the image classification, and the mean square error (MSE) between the feature vector of the input image and the standard feature vector is used to judge to which image groups the input image belongs. It has been proved that the method is not sensitivity with the Gaussian noise, salt and pepper noise or both of this and greatly robust for image recognition.
27
Qin, Tianyun, Rangding Wang, Diqun Yan, and Lang Lin. "Source Cell-Phone Identification in the Presence of Additive Noise from CQT Domain." Information 9, no. 8 (August 17, 2018): 205. http://dx.doi.org/10.3390/info9080205.
Full textAbstract:
With the widespread availability of cell-phone recording devices, source cell-phone identification has become a hot topic in multimedia forensics. At present, the research on the source cell-phone identification in clean conditions has achieved good results, but that in noisy environments is not ideal. This paper proposes a novel source cell-phone identification system suitable for both clean and noisy environments using spectral distribution features of constant Q transform (CQT) domain and multi-scene training method. Based on the analysis, it is found that the identification difficulty lies in different models of cell-phones of the same brand, and their tiny differences are mainly in the middle and low frequency bands. Therefore, this paper extracts spectral distribution features from the CQT domain, which has a higher frequency resolution in the mid-low frequency. To evaluate the effectiveness of the proposed feature, four classification techniques of Support Vector Machine (SVM), Random Forest (RF), Convolutional Neural Network (CNN) and Recurrent Neuron Network-Long Short-Term Memory Neural Network (RNN-BLSTM) are used to identify the source recording device. Experimental results show that the features proposed in this paper have superior performance. Compared with Mel frequency cepstral coefficient (MFCC) and linear frequency cepstral coefficient (LFCC), it enhances the accuracy of cell-phones within the same brand, whether the speech to be tested comprises clean speech files or noisy speech files. In addition, the CNN classification effect is outstanding. In terms of models, the model is established by the multi-scene training method, which improves the distinguishing ability of the model in the noisy environment than single-scenario training method. The average accuracy rate in CNN for clean speech files on the CKC speech database (CKC-SD) and TIMIT Recaptured Database (TIMIT-RD) databases increased from 95.47% and 97.89% to 97.08% and 99.29%, respectively. For noisy speech files with seen noisy types and unseen noisy types, the performance was greatly improved, and most of the recognition rates exceeded 90%. Therefore, the source identification system in this paper is robust to noise.
28
Lazic, Nevena, Amarnag Subramanya, Michael Ringgaard, and Fernando Pereira. "Plato: A Selective Context Model for Entity Resolution." Transactions of the Association for Computational Linguistics 3 (December 2015): 503–15. http://dx.doi.org/10.1162/tacl_a_00154.
Full textAbstract:
We present Plato, a probabilistic model for entity resolution that includes a novel approach for handling noisy or uninformative features, and supplements labeled training data derived from Wikipedia with a very large unlabeled text corpus. Training and inference in the proposed model can easily be distributed across many servers, allowing it to scale to over 107 entities. We evaluate Plato on three standard datasets for entity resolution. Our approach achieves the best results to-date on TAC KBP 2011 and is highly competitive on both the CoNLL 2003 and TAC KBP 2012 datasets.
29
Noh, Kyungjoo, Liang Jiang, and Bill Fefferman. "Efficient classical simulation of noisy random quantum circuits in one dimension." Quantum 4 (September 11, 2020): 318. http://dx.doi.org/10.22331/q-2020-09-11-318.
Full textAbstract:
Understanding the computational power of noisy intermediate-scale quantum (NISQ) devices is of both fundamental and practical importance to quantum information science. Here, we address the question of whether error-uncorrected noisy quantum computers can provide computational advantage over classical computers. Specifically, we study noisy random circuit sampling in one dimension (or 1D noisy RCS) as a simple model for exploring the effects of noise on the computational power of a noisy quantum device. In particular, we simulate the real-time dynamics of 1D noisy random quantum circuits via matrix product operators (MPOs) and characterize the computational power of the 1D noisy quantum system by using a metric we call MPO entanglement entropy. The latter metric is chosen because it determines the cost of classical MPO simulation. We numerically demonstrate that for the two-qubit gate error rates we considered, there exists a characteristic system size above which adding more qubits does not bring about an exponential growth of the cost of classical MPO simulation of 1D noisy systems. Specifically, we show that above the characteristic system size, there is an optimal circuit depth, independent of the system size, where the MPO entanglement entropy is maximized. Most importantly, the maximum achievable MPO entanglement entropy is bounded by a constant that depends only on the gate error rate, not on the system size. We also provide a heuristic analysis to get the scaling of the maximum achievable MPO entanglement entropy as a function of the gate error rate. The obtained scaling suggests that although the cost of MPO simulation does not increase exponentially in the system size above a certain characteristic system size, it does increase exponentially as the gate error rate decreases, possibly making classical simulation practically not feasible even with state-of-the-art supercomputers.
30
Zhang, Tian Chi, Jian Pei Zhang, Jing Zhang, and Melvyn L. Smith. "Two-Step Modified Nash Equilibrium Method for Medical Image Segmentation Based on an Improved C-V Model." Journal of Medical Imaging and Health Informatics 8, no. 9 (December 1, 2018): 1826–34. http://dx.doi.org/10.1166/jmihi.2018.2521.
Full textAbstract:
One of the most established region-based segmentation methods is the region based C-V model. This method formulates the image segmentation problem as a level set or improved level set clustering problem. However, the existing level set C-V model fails to perform well in the presence of noisy and incomplete data or when there is similarity between the objects and background, especially for clustering or segmentation tasks in medical images where objects appear vague and poorly contrasted in greyscale. In this paper, we modify the level set C-V model using a two-step modified Nash equilibrium approach. Firstly, a standard deviation using an entropy payoff approach is employed and secondly a two-step similarity clustering based approach is applied to the modified Nash equilibrium. One represents a maximum similarity within the clustered regions and the other the minimum similarity between the clusters. Finally, an improved C-V model based on a two-step modified Nash equilibrium is proposed to smooth the object contour during the image segmentation. Experiments demonstrate that the proposed method has good performance for segmenting noisy and poorly contrasting regions within medical images.
31
Monson, Christopher K., and Kevin D. Seppi. "A Graphical Model for Evolutionary Optimization." Evolutionary Computation 16, no. 3 (September 2008): 289–313. http://dx.doi.org/10.1162/evco.2008.16.3.289.
Full textAbstract:
We present a statistical model of empirical optimization that admits the creation of algorithms with explicit and intuitively defined desiderata. Because No Free Lunch theorems dictate that no optimization algorithm can be considered more efficient than any other when considering all possible functions, the desired function class plays a prominent role in the model. In particular, this provides a direct way to answer the traditionally difficult question of what algorithm is best matched to a particular class of functions. Among the benefits of the model are the ability to specify the function class in a straightforward manner, a natural way to specify noisy or dynamic functions, and a new source of insight into No Free Lunch theorems for optimization.
32
Yang, Lei, Haiqing Zhang, Daiwei Li, Fei Xiao, and Shanglin Yang. "Facial Expression Recognition Based on Transfer Learning and SVM." Journal of Physics: Conference Series 2025, no. 1 (September 1, 2021): 012015. http://dx.doi.org/10.1088/1742-6596/2025/1/012015.
Full textAbstract:
Abstract The facial expression datasets always have a problem: data with small amount or large amounts of data but also with large noisy. Both problems will affect the facial expression recognition accuracy of the model. A transfer learning method for facial expression recognition is proposed by combining the Convolutional Neural Network (CNN) and Support Vector Machine (SVM). SVM have good performance on small data sets and CNN based on transfer learning have better ability of feature extraction for large noisy data set. This method reduces the training time of model and increase the facial expression recognition accuracy. The experimental results show that the accuracy of the proposed method on the CK+ and FER2013 data sets has reached 99.6% and 68.1%.
33
Cedeño, Angel L., Ricardo Albornoz, Rodrigo Carvajal, Boris I. Godoy, and Juan C. Agüero. "A Two-Filter Approach for State Estimation Utilizing Quantized Output Data." Sensors 21, no. 22 (November 18, 2021): 7675. http://dx.doi.org/10.3390/s21227675.
Full textAbstract:
Filtering and smoothing algorithms are key tools to develop decision-making strategies and parameter identification techniques in different areas of research, such as economics, financial data analysis, communications, and control systems. These algorithms are used to obtain an estimation of the system state based on the sequentially available noisy measurements of the system output. In a real-world system, the noisy measurements can suffer a significant loss of information due to (among others): (i) a reduced resolution of cost-effective sensors typically used in practice or (ii) a digitalization process for storing or transmitting the measurements through a communication channel using a minimum amount of resources. Thus, obtaining suitable state estimates in this context is essential. In this paper, Gaussian sum filtering and smoothing algorithms are developed in order to deal with noisy measurements that are also subject to quantization. In this approach, the probability mass function of the quantized output given the state is characterized by an integral equation. This integral was approximated by using a Gauss–Legendre quadrature; hence, a model with a Gaussian mixture structure was obtained. This model was used to develop filtering and smoothing algorithms. The benefits of this proposal, in terms of accuracy of the estimation and computational cost, are illustrated via numerical simulations.
34
Peeters, Bert, and Ard Kuijpers. "Classification of noisy vehicles from unsupervised measurements." INTER-NOISE and NOISE-CON Congress and Conference Proceedings 265, no. 5 (February 1, 2023): 2175–84. http://dx.doi.org/10.3397/in_2022_0312.
Full textAbstract:
The NEMO-project (https://nemo-cities.eu/) aims to identify noisy and polluting road and rail vehicles, using remote sensing technology. Noise levels from individual road vehicles are measured from the roadside, in normal traffic. Road authorities may use these data to enforce noise limits, to limit access to Low Emission Zones or to influence driving behaviour. Whether a vehicle is a 'high noise emitter' is a complex question, as the noise level depends on vehicle type and condition, driving style, weather and location-specific characteristics. From a legal perspective, the question may be answered in relation to type approval noise limits, or in relation to local noise disturbance regulations. Within NEMO, a classification model is developed from a large dataset of unsupervised pass-by noise measurements, from different locations. The model labels noisy vehicles based on the noise measurements, technical vehicle data, driving conditions, and external factors. Several modeling and machine learning techniques were evaluated, to find the most accurate solution. This paper presents the results, and it looks forward to how the technological solution could be applied to enforce regulations, leading to a reduction of traffic noise annoyance.
35
Abdel Qader, Akram. "A New Novel Hybrid Dynamic Color Segmentation Model for Road Signs in Noisy Conditions." International Journal of Software Innovation 9, no. 3 (July 2021): 1–22. http://dx.doi.org/10.4018/ijsi.2021070101.
Full textAbstract:
Image segmentation is the most important process in road sign detection and classification systems. In road sign systems, the spatial information of road signs are very important for safety issues. Road sign segmentation is a complex segmentation task because of the different road sign colors and shapes that make it difficult to use specific threshold. Most road sign segmentation studies do good in ideal situations, but many problems need to be solved when the road signs are in poor lighting and noisy conditions. This paper proposes a hybrid dynamic threshold color segmentation technique for road sign images. In a pre-processing step, the authors use the histogram analysis, noise reduction with a Gaussian filter, adaptive histogram equalization, and conversion from RGB space to YCbCr or HSV color spaces. Next, a segmentation threshold is selected dynamically and used to segment the pre-processed image. The method was tested on outdoor images under noisy conditions and was able to accurately segment road signs with different colors (red, blue, and yellow) and shapes.
36
Rymarczyk, Tomasz, Krzysztof Polakowski, and Jan Sikora. "A NEW CONCEPT OF DISCRETIZATION MODEL FOR IMAGING IMPROVING IN ULTRASOUND TRANSMISSION TOMOGRAPHY." Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska 9, no. 4 (December 15, 2019): 48–51. http://dx.doi.org/10.35784/iapgos.131.
Full textAbstract:
In this paper a new version of discretization model for Ultrasonic Transmission Tomography is presented. The algorithm has been extensively tested for synthetic noisy data on various configurations of internal objects. In order to improve the imaging quality, the pixels/voxels have been enlarged compared to the figures inscribed in pixels/voxels however no more than figures described on the standard square pixels or cubic voxels. The proposed algorithm provides better quality of imaging.
37
Ji, S., and X. Yuan. "A GENERIC PROBABILISTIC MODEL AND A HIERARCHICAL SOLUTION FOR SENSOR LOCALIZATION IN NOISY AND RESTRICTED CONDITIONS." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLI-B1 (June 3, 2016): 193–98. http://dx.doi.org/10.5194/isprsarchives-xli-b1-193-2016.
Full textAbstract:
A generic probabilistic model, under fundamental Bayes’ rule and Markov assumption, is introduced to integrate the process of mobile platform localization with optical sensors. And based on it, three relative independent solutions, bundle adjustment, Kalman filtering and particle filtering are deduced under different and additional restrictions. We want to prove that first, Kalman filtering, may be a better initial-value supplier for bundle adjustment than traditional relative orientation in irregular strips and networks or failed tie-point extraction. Second, in high noisy conditions, particle filtering can act as a bridge for gap binding when a large number of gross errors fail a Kalman filtering or a bundle adjustment. Third, both filtering methods, which help reduce the error propagation and eliminate gross errors, guarantee a global and static bundle adjustment, who requires the strictest initial values and control conditions. The main innovation is about the integrated processing of stochastic errors and gross errors in sensor observations, and the integration of the three most used solutions, bundle adjustment, Kalman filtering and particle filtering into a generic probabilistic localization model. The tests in noisy and restricted situations are designed and examined to prove them.
38
Ji, S., and X. Yuan. "A GENERIC PROBABILISTIC MODEL AND A HIERARCHICAL SOLUTION FOR SENSOR LOCALIZATION IN NOISY AND RESTRICTED CONDITIONS." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLI-B1 (June 3, 2016): 193–98. http://dx.doi.org/10.5194/isprs-archives-xli-b1-193-2016.
Full textAbstract:
A generic probabilistic model, under fundamental Bayes’ rule and Markov assumption, is introduced to integrate the process of mobile platform localization with optical sensors. And based on it, three relative independent solutions, bundle adjustment, Kalman filtering and particle filtering are deduced under different and additional restrictions. We want to prove that first, Kalman filtering, may be a better initial-value supplier for bundle adjustment than traditional relative orientation in irregular strips and networks or failed tie-point extraction. Second, in high noisy conditions, particle filtering can act as a bridge for gap binding when a large number of gross errors fail a Kalman filtering or a bundle adjustment. Third, both filtering methods, which help reduce the error propagation and eliminate gross errors, guarantee a global and static bundle adjustment, who requires the strictest initial values and control conditions. The main innovation is about the integrated processing of stochastic errors and gross errors in sensor observations, and the integration of the three most used solutions, bundle adjustment, Kalman filtering and particle filtering into a generic probabilistic localization model. The tests in noisy and restricted situations are designed and examined to prove them.
39
Mayhew, Stephen, Gupta Nitish, and Dan Roth. "Robust Named Entity Recognition with Truecasing Pretraining." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 05 (April 3, 2020): 8480–87. http://dx.doi.org/10.1609/aaai.v34i05.6368.
Full textAbstract:
Although modern named entity recognition (NER) systems show impressive performance on standard datasets, they perform poorly when presented with noisy data. In particular, capitalization is a strong signal for entities in many languages, and even state of the art models overfit to this feature, with drastically lower performance on uncapitalized text. In this work, we address the problem of robustness of NER systems in data with noisy or uncertain casing, using a pretraining objective that predicts casing in text, or a truecaser, leveraging unlabeled data. The pretrained truecaser is combined with a standard BiLSTM-CRF model for NER by appending output distributions to character embeddings. In experiments over several datasets of varying domain and casing quality, we show that our new model improves performance in uncased text, even adding value to uncased BERT embeddings. Our method achieves a new state of the art on the WNUT17 shared task dataset.
40
Zhang, Jun, Wen Yao, Xiaoqian Chen, and Ling Feng. "Transferable Post-hoc Calibration on Pretrained Transformers in Noisy Text Classification." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 11 (June 26, 2023): 13940–48. http://dx.doi.org/10.1609/aaai.v37i11.26632.
Full textAbstract:
Recent work has demonstrated that pretrained transformers are overconfident in text classification tasks, which can be calibrated by the famous post-hoc calibration method temperature scaling (TS). Character or word spelling mistakes are frequently encountered in real applications and greatly threaten transformer model safety. Research on calibration under noisy settings is rare, and we focus on this direction. Based on a toy experiment, we discover that TS performs poorly when the datasets are perturbed by slight noise, such as swapping the characters, which results in distribution shift. We further utilize two metrics, predictive uncertainty and maximum mean discrepancy (MMD), to measure the distribution shift between clean and noisy datasets, based on which we propose a simple yet effective transferable TS method for calibrating models dynamically. To evaluate the performance of the proposed methods under noisy settings, we construct a benchmark consisting of four noise types and five shift intensities based on the QNLI, AG-News, and Emotion tasks. Experimental results on the noisy benchmark show that (1) the metrics are effective in measuring distribution shift and (2) transferable TS can significantly decrease the expected calibration error (ECE) compared with the competitive baseline ensemble TS by approximately 46.09%.
41
Bocquet, Marc, Julien Brajard, Alberto Carrassi, and Laurent Bertino. "Data assimilation as a learning tool to infer ordinary differential equation representations of dynamical models." Nonlinear Processes in Geophysics 26, no. 3 (July 10, 2019): 143–62. http://dx.doi.org/10.5194/npg-26-143-2019.
Full textAbstract:
Abstract. Recent progress in machine learning has shown how to forecast and, to some extent, learn the dynamics of a model from its output, resorting in particular to neural networks and deep learning techniques. We will show how the same goal can be directly achieved using data assimilation techniques without leveraging on machine learning software libraries, with a view to high-dimensional models. The dynamics of a model are learned from its observation and an ordinary differential equation (ODE) representation of this model is inferred using a recursive nonlinear regression. Because the method is embedded in a Bayesian data assimilation framework, it can learn from partial and noisy observations of a state trajectory of the physical model. Moreover, a space-wise local representation of the ODE system is introduced and is key to coping with high-dimensional models. It has recently been suggested that neural network architectures could be interpreted as dynamical systems. Reciprocally, we show that our ODE representations are reminiscent of deep learning architectures. Furthermore, numerical analysis considerations of stability shed light on the assets and limitations of the method. The method is illustrated on several chaotic discrete and continuous models of various dimensions, with or without noisy observations, with the goal of identifying or improving the model dynamics, building a surrogate or reduced model, or producing forecasts solely from observations of the physical model.
42
Zhang, Rui, Zhenghao Chen, Sanxing Zhang, Fei Song, Gang Zhang, Quancheng Zhou, and Tao Lei. "Remote Sensing Image Scene Classification with Noisy Label Distillation." Remote Sensing 12, no. 15 (July 24, 2020): 2376. http://dx.doi.org/10.3390/rs12152376.
Full textAbstract:
The widespread applications of remote sensing image scene classification-based Convolutional Neural Networks (CNNs) are severely affected by the lack of large-scale datasets with clean annotations. Data crawled from the Internet or other sources allows for the most rapid expansion of existing datasets at a low-cost. However, directly training on such an expanded dataset can lead to network overfitting to noisy labels. Traditional methods typically divide this noisy dataset into multiple parts. Each part fine-tunes the network separately to improve performance further. These approaches are inefficient and sometimes even hurt performance. To address these problems, this study proposes a novel noisy label distillation method (NLD) based on the end-to-end teacher-student framework. First, unlike general knowledge distillation methods, NLD does not require pre-training on clean or noisy data. Second, NLD effectively distills knowledge from labels across a full range of noise levels for better performance. In addition, NLD can benefit from a fully clean dataset as a model distillation method to improve the student classifier’s performance. NLD is evaluated on three remote sensing image datasets, including UC Merced Land-use, NWPU-RESISC45, AID, in which a variety of noise patterns and noise amounts are injected. Experimental results show that NLD outperforms widely used directly fine-tuning methods and remote sensing pseudo-labeling methods.
43
Tang, Ning, Zi-Long Fan, and Hao-Sheng Zeng. "Improving the quality of noisy spatial quantum channels." Quantum Information and Computation 15, no. 7&8 (May 2015): 568–81. http://dx.doi.org/10.26421/qic15.7-8-3.
Full textAbstract:
We show, for the non-Markovian or time-dependent Markovian model of noise, by breaking the noisy spatial quantum channel (SQC) into a series of periodically arranged sub-components, that the quality of information transmission described by the purity, fidelity and concurrence of the output states can be improved. The physical mechanism and possible implementation of the idea have been discussed.
44
Rohling, Jos H. T., and Janusz M. Meylahn. "Two-Community Noisy Kuramoto Model Suggests Mechanism for Splitting in the Suprachiasmatic Nucleus." Journal of Biological Rhythms 35, no. 2 (January 23, 2020): 158–66. http://dx.doi.org/10.1177/0748730419898314.
Full textAbstract:
Recent mathematical results for the noisy Kuramoto model on a 2-community network may explain some phenomena observed in the functioning of the suprachiasmatic nucleus (SCN). Specifically, these findings might explain the types of transitions to a state of the SCN in which 2 components are dissociated in phase, for example, in phase splitting. In contrast to previous studies, which required additional time-delayed coupling or large variation in the coupling strengths and other variations in the 2-community model to exhibit the phase-split state, this model requires only the 2-community structure of the SCN to be present. Our model shows that a change in the communication strengths within and between the communities due to external conditions, which changes the excitation-inhibition (E/I) balance of the SCN, may result in the SCN entering an unstable state. With this altered E/I balance, the SCN would try to find a new stable state, which might in some circumstances be the split state. This shows that the 2-community noisy Kuramoto model can help understand the mechanisms of the SCN and explain differences in behavior based on actual E/I balance.
45
Klawonn, Matthew, Eric Heim, and James Hendler. "Exploiting Class Learnability in Noisy Data." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 4082–89. http://dx.doi.org/10.1609/aaai.v33i01.33014082.
Full textAbstract:
In many domains, collecting sufficient labeled training data for supervised machine learning requires easily accessible but noisy sources, such as crowdsourcing services or tagged Web data. Noisy labels occur frequently in data sets harvested via these means, sometimes resulting in entire classes of data on which learned classifiers generalize poorly. For real world applications, we argue that it can be beneficial to avoid training on such classes entirely. In this work, we aim to explore the classes in a given data set, and guide supervised training to spend time on a class proportional to its learnability. By focusing the training process, we aim to improve model generalization on classes with a strong signal. To that end, we develop an online algorithm that works in conjunction with classifier and training algorithm, iteratively selecting training data for the classifier based on how well it appears to generalize on each class. Testing our approach on a variety of data sets, we show our algorithm learns to focus on classes for which the model has low generalization error relative to strong baselines, yielding a classifier with good performance on learnable classes.
46
Guo, Zhenyu, Yujuan Sun, Muwei Jian, and Xiaofeng Zhang. "Deep Residual Network with Sparse Feedback for Image Restoration." Applied Sciences 8, no. 12 (November 28, 2018): 2417. http://dx.doi.org/10.3390/app8122417.
Full textAbstract:
A deep neural network is difficult to train due to a large number of unknown parameters. To increase trainable performance, we present a moderate depth residual network for the restoration of motion blurring and noisy images. The proposed network has only 10 layers, and the sparse feedbacks are added in the middle and the last layers, which are called FbResNet. FbResNet has fast convergence speed and effective denoising performance. In addition, it can also reduce the artificial Mosaic trace at the seam of patches, and visually pleasant output results can be produced from the blurred images or noisy images. Experimental results show the effectiveness of our designed model and method.
47
Northcutt, Curtis, Lu Jiang, and Isaac Chuang. "Confident Learning: Estimating Uncertainty in Dataset Labels." Journal of Artificial Intelligence Research 70 (April 14, 2021): 1373–411. http://dx.doi.org/10.1613/jair.1.12125.
Full textAbstract:
Learning exists in the context of data, yet notions of confidence typically focus on model predictions, not label quality. Confident learning (CL) is an alternative approach which focuses instead on label quality by characterizing and identifying label errors in datasets, based on the principles of pruning noisy data, counting with probabilistic thresholds to estimate noise, and ranking examples to train with confidence. Whereas numerous studies have developed these principles independently, here, we combine them, building on the assumption of a class-conditional noise process to directly estimate the joint distribution between noisy (given) labels and uncorrupted (unknown) labels. This results in a generalized CL which is provably consistent and experimentally performant. We present sufficient conditions where CL exactly finds label errors, and show CL performance exceeding seven recent competitive approaches for learning with noisy labels on the CIFAR dataset. Uniquely, the CL framework is not coupled to a specific data modality or model (e.g., we use CL to find several label errors in the presumed error-free MNIST dataset and improve sentiment classification on text data in Amazon Reviews). We also employ CL on ImageNet to quantify ontological class overlap (e.g., estimating 645 missile images are mislabeled as their parent class projectile), and moderately increase model accuracy (e.g., for ResNet) by cleaning data prior to training. These results are replicable using the open-source cleanlab release.
48
Wu, Biao, Yong Huang, Xiang Chen, Sridhar Krishnaswamy, and Hui Li. "Guided-wave signal processing by the sparse Bayesian learning approach employing Gabor pulse model." Structural Health Monitoring 16, no. 3 (August 29, 2016): 347–62. http://dx.doi.org/10.1177/1475921716665252.
Full textAbstract:
Guided waves have been used for structural health monitoring to detect damage or defects in structures. However, guided wave signals often involve multiple modes and noise. Extracting meaningful damage information from the received guided wave signal becomes very challenging, especially when some of the modes overlap. The aim of this study is to develop an effective way to deal with noisy guided-wave signals for damage detection as well as for de-noising. To achieve this goal, a robust sparse Bayesian learning algorithm is adopted. One of the many merits of this technique is its good performance against noise. First, a Gabor dictionary is designed based on the information of the noisy signal. Each atom of this dictionary is a modulated Gaussian pulse. Then the robust sparse Bayesian learning technique is used to efficiently decompose the guided wave signal. After signal decomposition, a two-step matching scheme is proposed to extract meaningful waveforms for damage detection and localization. Results from numerical simulations and experiments on isotropic aluminum plate structures are presented to verify the effectiveness of the proposed approach in mode identification and signal de-noising for damage detection.
49
Kaur, Inderjit, and Dr Pardeep Saini. "Classifier Model using Artificial Neural Network." International Journal of Engineering, Business and Management 7, no. 4 (2023): 69–73. http://dx.doi.org/10.22161/ijebm.7.4.11.
Full textAbstract:
When it comes to AI and ML, precision in categorization is of the utmost importance. In this research, the use of supervised instance selection (SIS) to improve the performance of artificial neural networks (ANNs) in classification is investigated. The goal of SIS is to enhance the accuracy of future classification tasks by identifying and selecting a subset of examples from the original dataset. The purpose of this research is to provide light on how useful SIS is as a preprocessing tool for artificial neural network-based classification. The work aims to improve the input dataset to ANNs by using SIS, which may help with problems caused by noisy or redundant data. The ultimate goal is to improve ANNs' ability to identify data points properly across a wide range of application areas.
50
Stark, Oliver, Martin Pfeifer, and Sören Hohmann. "Parameter and Order Identification of Fractional Systems with Application to a Lithium-Ion Battery." Mathematics 9, no. 14 (July 8, 2021): 1607. http://dx.doi.org/10.3390/math9141607.
Full textAbstract:
This paper deals with a method for the parameter and order identification of a fractional model. In contrast to existing approaches that can either handle noisy observations of the output signal or systems that are not at rest, the proposed method does not have to compromise between these two characteristics. To handle systems that are not at rest, the parameter, as well as the order identification, are based on the modulating function method. The novelty of the proposed method is that an optimization-based approach is used for the order identification. Thus, even if only noisy observations of the output signal are available, an approximate identification can be performed. The proposed identification method is, then, applied to identify the parameters and orders of a lithium-ion battery model. The experimental results illustrate the practical usefulness and verify the validity of our approach.