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
Proceedings ArticleDOI
A Brief Review on Deep Learning in Application of Communication Signal Processing
TL;DR: This paper presents a brief review on deep learning in application of communication signal processing and several challenges confronted by application of deep learning technology in communication signalprocessing are proposed.
Proceedings ArticleDOI
Discriminability-Transferability Trade-Off: An Information-Theoretic Perspective
Quan Cui,Bingchen Zhao,Zhaoming Chen,Bo-Rui Zhao,Ren-Jie Song,Jiajun Liang,Boyan Zhou,Osamu Yoshie +7 more
TL;DR: In this article , Liu et al. proposed contrastive temporal coding (CTC) to counteract the over-compression and alleviate the incompatibility between discriminability and transferability.
Proceedings ArticleDOI
Seq2Bubbles: Region-Based Embedding Learning for User Behaviors in Sequential Recommenders
TL;DR: Zhang et al. as discussed by the authors proposed Seq2Bubbles, a new representation model for sequential user behaviors via embedding an input sequence into a set of bubbles each of which is represented by a center vector and a radius vector in embedding space.
Posted Content
Interpreting Deep Learning: The Machine Learning Rorschach Test?
TL;DR: The interpretation of DNNs appears to mimic a type of Rorschach test --- a psychological test wherein subjects interpret a series of seemingly ambiguous ink-blots, which requires a convergence of the literature.
Posted Content
Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction
TL;DR: The Maximal Coding Rate Reduction (MCR) as discussed by the authors is an information-theoretic measure that maximizes the coding rate difference between the whole dataset and the sum of each individual class.
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.