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
Earthquake Phase Association with Graph Neural Networks
TL;DR: The Graph Earthquake Neural Interpretation Engine (GENIE) as discussed by the authors uses a graph neural network associator that simultaneously predicts both source space-time localization and discrete source-arrival association likelihoods.
Posted Content
Intelligence plays dice: Stochasticity is essential for machine learning
TL;DR: It is argued that stochasticity plays a fundamentally different role in machine learning (ML) and is likely a critical ingredient of intelligent systems.
Journal ArticleDOI
BDA-SketRet: Bi-Level Domain Adaptation for Zero-Shot SBIR
TL;DR: Zhang et al. as discussed by the authors proposed BDA-SketRet, a novel zero-shot sketch-based image retrieval (ZS-SBIR) framework performing a bi-level domain adaptation for aligning the spatial and semantic features of the visual data pairs progressively.
Posted Content
On the Maximum Mutual Information Capacity of Neural Architectures.
Brandon Foggo,Nanpeng Yu +1 more
TL;DR: It is shown that the maximum mutual information of an architecture is most strongly influenced by the width of the smallest layer of the network - the "information bottleneck" in a different sense of the phrase, and by any statistical invariances captured by the architecture.
Journal ArticleDOI
Mitigating severe over-parameterization in deep convolutional neural networks through forced feature abstraction and compression with an entropy-based heuristic
TL;DR: An Entropy-Based Convolutional Layer Estimation (EBCLE) heuristic which is robust and simple, yet effective in resolving the problem of over-parameterization with regards to network depth of CNN model is proposed.
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.