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
Posted Content
Partially Observable Szilard Engines
Susanne Still,Dorian Daimer +1 more
TL;DR: In this article, the authors proposed a generalized, partially observable information engine (Szilard engine), which can run work extraction at a different temperature from the memory forming process, thus allowing for the combined treatment of heat and information engines.
Journal ArticleDOI
Rationalizing predictions by adversarial information calibration
TL;DR: In this paper , an adversarial technique is used to calibrate the information extracted by the two models such that the difference between them is an indicator of the missed or over-selected features.
Journal Article
A Local Geometric Interpretation of Feature Extraction in Deep Feedforward Neural Networks
TL;DR: A local geometric analysis to interpret how deep feedforward neural networks extract lowdimensional features from high-dimensional data shows that the optimal weight in one layer of the neural network and the optimal feature generated by the previous layer comprise a low-rank approximation of a matrix that is determined by the Bayes action of this layer.
Using function space theory for understanding intermediate layers
Oren Elisha,Shai Dekel +1 more
TL;DR: It is argued that a weak-type Besov smoothness index can quantify the geometry of the clustering in the feature space of each layer of a neural network, and may provide an additional perspective for understanding data-models fit in the setting of deep learning.
Journal ArticleDOI
Faithful and Consistent Graph Neural Network Explanations with Rationale Alignment
TL;DR: In this paper , a new explanation framework with an auxiliary alignment loss is proposed, which is theoretically proven to be optimizing a more faithful explanation objective intrinsically, and a comprehensive study is conducted both on the effectiveness of this new framework in terms of explanation faithfulness/consistency and on the advantages of these variants.
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.