Deep learning and the information bottleneck principle
Naftali Tishby,Noga Zaslavsky +1 more
- pp 1-5
TLDR
It is argued that both the optimal architecture, number of layers and features/connections at each layer, are related to the bifurcation points of the information bottleneck tradeoff, namely, relevant compression of the input layer with respect to the output layer.Abstract:
Deep Neural Networks (DNNs) are analyzed via the theoretical framework of the information bottleneck (IB) principle. We first show that any DNN can be quantified by the mutual information between the layers and the input and output variables. Using this representation we can calculate the optimal information theoretic limits of the DNN and obtain finite sample generalization bounds. The advantage of getting closer to the theoretical limit is quantifiable both by the generalization bound and by the network's simplicity. We argue that both the optimal architecture, number of layers and features/connections at each layer, are related to the bifurcation points of the information bottleneck tradeoff, namely, relevant compression of the input layer with respect to the output layer. The hierarchical representations at the layered network naturally correspond to the structural phase transitions along the information curve. We believe that this new insight can lead to new optimality bounds and deep learning algorithms.read more
Citations
More filters
Journal ArticleDOI
Information-Theoretic Odometry Learning
Sen Zhang,Jing Zhang,Dacheng Tao +2 more
TL;DR: In this paper , a unified information theoretic framework for learning-motivated methods aimed at odometry estimation is proposed, which eliminates pose-irrelevant information from the latent representation.
Journal ArticleDOI
Comprehending the impact of deep learning algorithms on optimizing for recurring impediments associated with stress prediction using ECG data through statistical analysis
TL;DR: In this paper , the authors used transfer learning and autoencoder techniques to predict stress/not stress (2 classes) with high precision from the WESAD dataset, achieving a 98.99% (CNN) and 98.92% (VGG16) accuracy.
Posted Content
Adversarial Mutual Information for Text Generation
Boyuan Pan,Yazheng Yang,Kaizhao Liang,Bhavya Kailkhura,Zhongming Jin,Xian-Sheng Hua,Deng Cai,Bo Li +7 more
TL;DR: This paper proposes Adversarial Mutual Information (AMI): a text generation framework which is formed as a novel saddle point (min-max) optimization aiming to identify joint interactions between the source and target and develops a latent noise sampling strategy that leverages random variations at the high-level semantic space to enhance the long term dependency in the generation process.
Posted Content
Adaptive structured noise injection for shallow and deep neural networks
TL;DR: This work proposes a generalisation of dropout and other multiplicative noise injection schemes for shallow and deep neural networks, where the random noise applied to different units is not independent but follows a joint distribution that is either fixed or estimated during training.
Proceedings ArticleDOI
A Functional Information Perspective on Model Interpretation
TL;DR: This work suggests a theoretical framework for model interpretability by measuring the contribution of relevant features to the functional entropy of the network with respect to the input by relying on the log-Sobolev inequality.
References
More filters
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Book
Elements of information theory
Thomas M. Cover,Joy A. Thomas +1 more
TL;DR: The author examines the role of entropy, inequality, and randomness in the design of codes and the construction of codes in the rapidly changing environment.
Journal ArticleDOI
Reducing the Dimensionality of Data with Neural Networks
TL;DR: In this article, an effective way of initializing the weights that allows deep autoencoder networks to learn low-dimensional codes that work much better than principal components analysis as a tool to reduce the dimensionality of data is described.
Journal ArticleDOI
Representation Learning: A Review and New Perspectives
TL;DR: Recent work in the area of unsupervised feature learning and deep learning is reviewed, covering advances in probabilistic models, autoencoders, manifold learning, and deep networks.
Book
Learning Deep Architectures for AI
TL;DR: The motivations and principles regarding learning algorithms for deep architectures, in particular those exploiting as building blocks unsupervised learning of single-layer modelssuch as Restricted Boltzmann Machines, used to construct deeper models such as Deep Belief Networks are discussed.