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
The Variational Deficiency Bottleneck
TL;DR: It is shown that the deficiency of one channel with respect to another has an operational interpretation in terms of the optimal risk gap of decision problems, capturing classification as a special case.
Proceedings ArticleDOI
Controllable Gradient Item Retrieval
TL;DR: In this article, a weakly supervised method is proposed to learn a disentangled item representation from user-item interaction data and ground the semantic meaning of attributes to dimensions of the item representation.
Posted Content
A Differential Topological View of Challenges in Learning with Feedforward Neural Networks
TL;DR: This work offers a differential topological view of loss landscape of DNNs, interplay between width and depth in expressibility, and regularisations for generalisability, and further applies the quotient topology to investigate the architecture of Dnns, which enables to capture nuisance factors in data with respect to a specific learning task.
Proceedings ArticleDOI
Secure Triplet Loss for End-to-End Deep Biometrics
TL;DR: Although further efforts are needed to avoid template linkability, the proposed secure triplet loss shows promise in template cancelability and non-invertibility for biometric recognition while taking advantage of the full power of convolutional neural networks.
Journal ArticleDOI
MOOC Dropout Prediction Based on Multidimensional Time-Series Data
TL;DR: This paper proposes a dropout prediction model that combines a multiscale fully convolutional network and a variational information bottleneck and shows that the proposed method achieved the best performance compared to the baseline method.
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.