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 Article
Entropy and mutual information in models of deep neural networks
Marylou Gabrié,Andre Manoel,Clément Luneau,Jean Barbier,Nicolas Macris,Florent Krzakala,Lenka Zdeborová +6 more
TL;DR: In this article, the authors examined a class of stochastic deep learning models with a tractable method to compute information-theoretic quantities, such as entropies and mutual informations.
Journal ArticleDOI
A Deep Information Sharing Network for Multi-Contrast Compressed Sensing MRI Reconstruction
TL;DR: Wang et al. as discussed by the authors proposed the first deep learning model for multi-contrast CS-MRI reconstruction, which achieved information sharing through feature sharing units, which significantly reduced the number of model parameters.
Posted Content
Uncertainty in the Variational Information Bottleneck
TL;DR: A simple case study is presented, demonstrating that Variational Information Bottleneck can improve a network's classification calibration as well as its ability to detect out-of-distribution data.
Journal ArticleDOI
Detecting Cyberbullying and Cyberaggression in Social Media
Despoina Chatzakou,Ilias Leontiadis,Jeremy Blackburn,Emiliano De Cristofaro,Gianluca Stringhini,Athena Vakali,Nicolas Kourtellis +6 more
TL;DR: This work presents a robust methodology to distinguish bullies and aggressors from normal Twitter users by considering text, user, and network-based attributes, and discusses the current status of Twitter user accounts marked as abusive by the methodology and the performance of potential mechanisms that can be used by Twitter to suspend users in the future.
Book ChapterDOI
Learning to Learn with Variational Information Bottleneck for Domain Generalization
TL;DR: A probabilistic meta-learning model for domain generalization is introduced, in which classifier parameters shared across domains are modeled as distributions, which enables better handling of prediction uncertainty on unseen domains.
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.