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 ArticleDOI
Shade: Information-Based Regularization for Deep Learning
TL;DR: In this article, the authors propose a new information-theory-based regularization scheme named SHADE for SHAnnon DEcay, which explicitly decouples the learning of invariant representations in the regularizer and the learned of correlations between inputs and labels in the data fitting term.
Proceedings Article
Information Competing Process for Learning Diversified Representations
TL;DR: Experiments on image classification and image reconstruction tasks demonstrate the great potential of ICP to learn discriminative and disentangled representations in both supervised and self-supervised learning settings.
Proceedings ArticleDOI
How are attributes expressed in face DCNNs
Prithviraj Dhar,Ankan Bansal,Carlos D. Castillo,Joshua Gleason,P. Jonathon Phillips,Rama Chellappa +5 more
TL;DR: In this article, the authors investigated the expressivity of facial attributes for two different deep convolutional neural network (DCNN) architectures: a Resnet-101 and an Inception Resnet v2.
Proceedings ArticleDOI
Neural Models of Ferrite Inductors Non-Linear Behavior
TL;DR: The proposed feedforward neural model is verified on commercial FC power inductors via numerical simulations, thus allowing the validation of the proposed neural model and open up the possibility of including the problem of modelling the non-linear characteristic of inductors in the great field of deep learning research.
Posted Content
Neural network representation of electronic structure from ab initio molecular dynamics.
TL;DR: In this paper, a transferable high-fidelity neural network representation of electronic structure data in the form of tight-binding Hamiltonians for crystalline materials was introduced. But the model was not applied to a one-dimensional charge-density wave material, carbyne.
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.