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
Posted Content
Holographic entanglement renormalisation of topological order in a quantum liquid
Anirban Mukherjee,Siddhartha Lal +1 more
TL;DR: A deep neural network (DNN) architecture is constructed based on the EHM network, and it is demonstrated that the DNN is capable of distinguishing between the topologically ordered and gapless normal metallic phases.
Dissertation
A Geometric Approach to Biomedical Time Series Analysis
TL;DR: The wave-shape oscillatory model can be well-recovered by applying the diffusion maps algorithm to the time series’ set of oscillatory cycles.
Proceedings ArticleDOI
Reversible Column Networks
TL;DR: In this article , the authors proposed a Reversible Column Network (RevCol) which is composed of multiple copies of subnetworks, named columns respectively, between which multi-level reversible connections are employed.
Journal ArticleDOI
Unsupervised bin-wise pre-training: A fusion of information theory and hypergraph
TL;DR: A novel unsupervised bin-wise pre-training model which fuses Information Theory and Hypergraph that acts as an effective optimizer: speed up the learning process & minimize generalization loss, and also as an impelling regularizer: maintain the stability of the Deep Neural Network is presented.
Proceedings ArticleDOI
Preliminary Application of Deep Learning to Design Space Exploration
TL;DR: This paper proposes using Deep Neural Networks (DNN) as a solution to cover the large design space using their generalization capability, i.e., predicting outside the range of training data.
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.