Brofos, James A; Shu, Rui; Lederman, Roy R A Bias-Variance Decomposition for Bayesian Deep Learning Inproceedings pp. 14, 2019. Abstract | BibTeX | Tags: Bayesian Deep Learning, Bayesian Inference, Deep Learning @inproceedings{brofos_bias-variance_2019, title = {A Bias-Variance Decomposition for Bayesian Deep Learning}, author = {James A Brofos and Rui Shu and Roy R Lederman}, year = {2019}, date = {2019-12-01}, pages = {14}, abstract = {We exhibit a decomposition of the Kullback-Leibler divergence into terms corresponding to bias, variance, and irreducible error. Our particular focus in this work is Bayesian deep learning and in this domain we illustrate the application of this decomposition to adversarial example identification, to image segmentation, and to malware detection. We empirically demonstrate qualitative similarities between the variance decomposition and mutual information.}, keywords = {Bayesian Deep Learning, Bayesian Inference, Deep Learning}, pubstate = {published}, tppubtype = {inproceedings} } We exhibit a decomposition of the Kullback-Leibler divergence into terms corresponding to bias, variance, and irreducible error. Our particular focus in this work is Bayesian deep learning and in this domain we illustrate the application of this decomposition to adversarial example identification, to image segmentation, and to malware detection. We empirically demonstrate qualitative similarities between the variance decomposition and mutual information. |
Shaham, Uri; Lederman, Roy R Learning by coincidence: Siamese networks and common variable learning Journal Article Pattern Recognition, 74 , pp. 52–63, 2018, ISSN: 00313203. Links | BibTeX | Tags: Common variable, Deep Learning, Multi-view, multimodal, Siamese networks @article{shaham_learning_2018, title = {Learning by coincidence: Siamese networks and common variable learning}, author = {Uri Shaham and Roy R Lederman}, url = {https://linkinghub.elsevier.com/retrieve/pii/S0031320317303588}, doi = {10.1016/j.patcog.2017.09.015}, issn = {00313203}, year = {2018}, date = {2018-01-01}, urldate = {2020-08-13}, journal = {Pattern Recognition}, volume = {74}, pages = {52--63}, keywords = {Common variable, Deep Learning, Multi-view, multimodal, Siamese networks}, pubstate = {published}, tppubtype = {article} } |
Shaham, Uri; Lederman, Roy R Common Variable Learning and Invariant Representation Learning using Siamese Neural Networks Technical Report 2015. Abstract | Links | BibTeX | Tags: Common variable, Deep Learning, Multi-view @techreport{shaham_common_2015, title = {Common Variable Learning and Invariant Representation Learning using Siamese Neural Networks}, author = {Uri Shaham and Roy R Lederman}, url = {https://arxiv.org/abs/1512.08806v3}, year = {2015}, date = {2015-12-01}, urldate = {2020-08-13}, abstract = {We consider the statistical problem of learning common source of variability in data which are synchronously captured by multiple sensors, and demonstrate that Siamese neural networks can be naturally applied to this problem. This approach is useful in particular in exploratory, data-driven applications, where neither a model nor label information is available. In recent years, many researchers have successfully applied Siamese neural networks to obtain an embedding of data which corresponds to a "semantic similarity". We present an interpretation of this "semantic similarity" as learning of equivalence classes. We discuss properties of the embedding obtained by Siamese networks and provide empirical results that demonstrate the ability of Siamese networks to learn common variability.}, keywords = {Common variable, Deep Learning, Multi-view}, pubstate = {published}, tppubtype = {techreport} } We consider the statistical problem of learning common source of variability in data which are synchronously captured by multiple sensors, and demonstrate that Siamese neural networks can be naturally applied to this problem. This approach is useful in particular in exploratory, data-driven applications, where neither a model nor label information is available. In recent years, many researchers have successfully applied Siamese neural networks to obtain an embedding of data which corresponds to a "semantic similarity". We present an interpretation of this "semantic similarity" as learning of equivalence classes. We discuss properties of the embedding obtained by Siamese networks and provide empirical results that demonstrate the ability of Siamese networks to learn common variability. |