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
QuASE: Question-Answer Driven Sentence Encoding.
Hangfeng He,Qiang Ning,Dan Roth +2 more
TL;DR: This article propose the question-answer driven sentence encoding (QuASE) framework, which learns representations from QA data, using BERT or other state-of-the-art contextual language models.
Posted Content
What is Semantic Communication? A View on Conveying Meaning in the Era of Machine Intelligence.
TL;DR: In this paper, the authors present a view of semantic communication and conveying meaning through the communication systems, including human-to-human (H2H), H2M, and M2M communications.
Proceedings Article
Curiosity-Bottleneck: Exploration By Distilling Task-Specific Novelty.
TL;DR: This work shows that Curiosity-Bottleneck learns an effective exploration strategy by robustly measuring the state novelty in distractive environments where state-of-the-art exploration methods often degenerate.
Posted Content
Privacy-Preserving Deep Neural Networks with Pixel-based Image Encryption Considering Data Augmentation in the Encrypted Domain
TL;DR: In this paper, a pixel-based image encryption method is proposed for privacy-preserving deep neural networks (DNNs) that enables them not only apply images without visual information to DNNs for both training and testing, but also consider data augmentation in the encrypted domain for the first time.
Posted Content
Information-Distilling Quantizers.
TL;DR: In this paper, the authors consider the problem of designing a scalar quantizer for a dependent random variable to maximize the mutual information between the quantizer's output and the target variable, and develop fundamental properties and bounds for this form of quantization.
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.