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
Estimators for Multivariate Information Measures in General Probability Spaces
TL;DR: In this paper, a general graph divergence measure (GDM) was defined and a coupling trick was used to directly estimate multivariate information measures using the Radon-Nikodym derivative.
Posted Content
Translation Error Detection as Rationale Extraction.
TL;DR: The authors used a set of feature attribution methods that assign relevance scores to the inputs to explain model predictions and showed that explanations extracted from these models can indeed be used to detect translation errors.
Journal Article
Task-Oriented Semantic Communication Systems Based on Extended Rate-Distortion Theory
TL;DR: An extended rate-distortion theory which considers both concise representation and semantic distortion is presented and a task-oriented semantic image communication system is proposed which outperforms the traditional and multi-task based communication system in terms of task performance at the same signal compression degree and noise interference degree.
Journal ArticleDOI
On the Difference between the Information Bottleneck and the Deep Information Bottleneck
Aleksander Wieczorek,Volker Roth +1 more
TL;DR: This paper revisits the deep variational information bottleneck and proposes interpreting the family of information bottleneck models as directed graphical models, and shows that in this framework, the original and deep information bottlenecks are special cases of a fundamental IB model.
Journal ArticleDOI
Indoor Positioning System using Regression-based Fingerprint Method
TL;DR: A deep regression machine learning using convolutional neural network (CNN) with regression-based fingerprint model to estimate real position and demonstrates that the proposed method outperformed the benchmark methods.
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.