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
Performance Evaluation of Deep Learning Models for Image Classification Over Small Datasets: Diabetic Foot Case Study
Abian Hernandez-Guedes,Idafen Santana-Perez,N. Arteaga-Marrero,Himar Fabelo,Gustavo M. Callico,Juan Ruiz-Alzola +5 more
TL;DR: In this paper , an innovative approach is proposed to evaluate the performance of DL models when labeled data is scarce, which aims to detect the poor performance provided by DL models, in spite of traditional assessing metrics indicating otherwise.
Posted Content
Conceptual Content in Deep Convolutional Neural Networks: An analysis into multi-faceted properties of neurons
TL;DR: In this paper, the responses of neurons to the images of classes in ImageNet database are analyzed based on the convolutional layers of pre-trained VGG16 model, and the results demonstrate that the neurons in lower layers exhibit a multi-faceted behavior, whereas the majority of neurons in higher layers com-prise single-folded property and tend to respond to a smaller number of concepts.
Journal ArticleDOI
Dual Attention and Patient Similarity Network for drug recommendation
TL;DR: In this article , the authors proposed DAPSNet, which encodes multi-type medical codes into patient representations through code-and visit-level attention mechanisms, while integrating drug information corresponding to similar patient states to improve the performance of drug recommendation.
Proceedings ArticleDOI
Structured Refinement for Sequential Labeling
TL;DR: This paper proposes to extend previous work with globally normalized attention, e.g., structured attention, to leverage structural information for more effective representation refinement, and provides extensive experimental results on various datasets to show the effectiveness and efficiency of the proposed method.
Dissertation
An Information-Theoretic Approach to Distributed Learning. Distributed Source Coding Under Logarithmic Loss
TL;DR: In this article, Courtade-Weissman et al. investigated the problem of perte logarithmique in the context of information distorption and showed that the problem can be solved by using a probabilistic model.
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.