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
Learning to Find Correlated Features by Maximizing Information Flow in Convolutional Neural Networks
TL;DR: This work proposes an information flow maximization (IFM) loss as a regularization term to find the discriminative correlated features and validates the method on the shiftedMNIST dataset and shows the effectiveness of IFM loss in learning representative and discriminatives features.
Proceedings Article
Information Laundering for Model Privacy
TL;DR: In this paper, the authors propose information laundering, a framework for enhancing model privacy, which aims to protect an already-learned model that is to be deployed for public use and can return a deterministic or random response for a given input query.
Journal ArticleDOI
Machine Learning in Tissue Engineering
TL;DR: A recent review as discussed by the authors highlights the novel methodologies, emerging strategies, and areas of potential growth within this rapidly evolving area of research, including machine-optimized biomaterial design, predictive modeling of scaffold fabrication, and spatiotemporal analysis of cell and tissue systems.
Journal ArticleDOI
Unsupervised Heterophilous Network Embedding via r-Ego Network Discrimination
TL;DR: The first empirical study on the impact of homophily ratio on the performance of existing unsupervised NE methods and reveals their limitations is introduced and a SELf-supErvised Network Embedding (Selene) framework is developed for learning useful node representations for both homophilous and heterophILous networks.
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.