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
Icentia11K: An Unsupervised Representation Learning Dataset for Arrhythmia Subtype Discovery.
Shawn Tan,Guillaume Androz,Ahmad Chamseddine,Pierre Fecteau,Aaron Courville,Yoshua Bengio,Joseph Paul Cohen +6 more
TL;DR: The largest public ECG dataset of continuous raw signals for representation learning containing 11 thousand patients and 2 billion labelled beats is released and a set of baselines for different feature extractors that can be built upon are provided.
Posted Content
Minimal Achievable Sufficient Statistic Learning
TL;DR: In a series of experiments, it is shown that deep networks trained with MASS Learning achieve competitive performance on supervised learning and uncertainty quantification benchmarks.
Journal ArticleDOI
Exploiting deep representations for natural language processing
TL;DR: Experimental results on both machine translation and language representation tasks demonstrate the effectiveness and universality of the proposed approaches, which indicates the necessity of exploiting deep representations for natural language processing tasks.
Journal ArticleDOI
Penetrating the influence of regularizations on neural network based on information bottleneck theory
TL;DR: A metric is proposed to characterise the encoding length of hidden layers, named as AEntry value, to give insight into building more efficient regularization algorithm to improve the performance of neural network model.
Proceedings ArticleDOI
On the Security of Pixel-Based Image Encryption for Privacy-Preserving Deep Neural Networks
TL;DR: Wang et al. as discussed by the authors proposed a pixel-based image encryption method, which has been proposed to apply images with no visual information to deep neural networks (DNN), in terms of robustness against ciphertext-only attacks (COA).
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.