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
BookDOI
Advanced concepts for intelligent vision systems, 19th international conference, ACIVS 2018, proceedings
TL;DR: This book constitutes the refereed proceedings of the 19th International Conference on Advanced Concepts for Intelligent Vision Systems, ACIVS 2018, held in Poitiers, France, in September 2018.
Proceedings ArticleDOI
Mutual Information Maximization for Simple and Accurate Part-Of-Speech Induction
TL;DR: This work addresses part-of-speech (POS) induction by maximizing the mutual information between the induced label and its context and shows that the variational lower bound is robust whereas the generalized Brown objective is vulnerable.
Journal ArticleDOI
Scalable Image Coding for Humans and Machines
TL;DR: In this article , an end-to-end learned image codec whose latent space is designed to support scalability from simpler to more complicated tasks is presented. But the authors focus on the task of image reconstruction.
Posted Content
Learning Optimal Representations with the Decodable Information Bottleneck
TL;DR: This work proposes the Decodable Information Bottleneck (DIB), a framework that considers information retention and compression from the perspective of the desired predictive family and gives rise to representations that are optimal in terms of expected test performance and can be estimated with guarantees.
Posted Content
Processing Bias: Extending Sensory Drive to Include Efficacy and Efficiency in Information Processing
TL;DR: A sensory drive model that incorporates processing bias hypothesizes a causal chain of relationships between the environment, perception, pleasure, preference and ultimately the evolution of signal design, both simple and complex.
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.