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
Pixel-CRN: A New Machine Learning Approach for Convective Storm Nowcasting
TL;DR: In this paper , a pixelwise convolutional-recurrent neural network (Pixel-CRN) is proposed for short-term convective storm forecasting, which uses 3D reanalysis data.
Journal ArticleDOI
Improving the Trainability of Deep Neural Networks through Layerwise Batch-Entropy Regularization
TL;DR: It is proved empirically and theoretically that a positive batch-entropy is required for gradient descent-based training approaches to optimize a given loss function successfully, and it is shown that a "vanilla" fully connected network and convolutional neural network can be trained with no skip connections, batch normalization, dropout, or any other architectural tweak.
Posted Content
GILBO: One Metric to Measure Them All
Alexander A. Alemi,Ian Fischer +1 more
TL;DR: A simple, tractable lower bound on the mutual information contained in the joint generative density of any latent variable generative model: the GILBO (Generative Information Lower BOund), giving the log of the effective description length.
Journal ArticleDOI
Pixel-CRN: A New Machine Learning Approach for Convective Storm Nowcasting
TL;DR: In this article , a pixel-wise convolutional recurrent neural network (Pixel-CRN) was proposed for short-term convective storm forecasting using only a small dataset.
Journal ArticleDOI
Infor-Coef: Information Bottleneck-based Dynamic Token Downsampling for Compact and Efficient language model
TL;DR: This article proposed a model accelaration approach for large language models that incorporates dynamic token downsampling and static pruning, optimized by the information bottleneck loss, which achieved an 18x FLOPs speedup with an accuracy degradation of less than 8% compared to BERT.
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.