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
Statistical Mechanics of On-Line Learning Under Concept Drift.
TL;DR: A modeling framework for the investigation of on-line machine learning processes in non-stationary environments is introduced and it is shown that LVQ is capable of tracking a classification scheme under drift to a non-trivial extent and that concept drift can cause the persistence of sub-optimal plateau states in gradient based training of layered neural networks for regression.
Proceedings ArticleDOI
Convexity and Operational Interpretation of the Quantum Information Bottleneck Function
TL;DR: In this article, an operational interpretation of the quantum information bottleneck method as an optimal rate of a bona fide information-theoretic task, namely that of quantum source coding with quantum side information at the decoder, which has recently been solved by Hsieh and Watanabe, is presented.
Journal ArticleDOI
Modality-Invariant Asymmetric Networks for Cross-Modal Hashing
TL;DR: Li et al. as mentioned in this paper proposed a modality-invariant asymmetric networks (MIAN) architecture, which explores the asymmetric intra- and inter-modal similarity preservation under a probabilistic modality alignment framework.
The free energy principle made simpler but not too simple
Karl J. Friston,Lancelot Da Costa,Noor Sajid,Conor Heins,Kai Ueltzhoffer,Grigorios A. Pavliotis,Thomas E. Parr +6 more
TL;DR: This paper provides a concise description of the free energy principle, starting from a formulation of random dynamical systems in terms of a Langevin equation and ending with a Bayesian mechanics that can be read as a physics of sentience.
Journal ArticleDOI
Averaging Is Probably Not the Optimum Way of Aggregating Parameters in Federated Learning.
TL;DR: The results confirm the correlation between different clients and show an increasing trend of mutual information with training iteration, but when the distance between client computed parameters is computed, it is found that parameters are getting more correlated while not getting closer, suggesting that averaging parameters may not be the optimum way of aggregating trained parameters.
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.