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
Invariant Representations with Stochastically Quantized Neural Networks
TL;DR: This paper employs stochastically-activated binary neural networks and compute (not bound) the mutual information between a layer and a sensitive attribute and use this information as a regularization factor during gradient descent and shows that the learned representations display a higher level of invariance compared to full-precision neural networks.
Journal ArticleDOI
WaGI : Wavelet-based GAN Inversion for Preserving High-frequency Image Details
TL;DR: This paper proposes a novel GAN inversion model, coined WaGI, which enables to handle high-frequency features explicitly, by using a novel wavelet-based loss term and a newly proposed wavelet fusion scheme.
Journal ArticleDOI
SceneTrilogy: On Scene Sketches and its Relationship with Text and Photo
TL;DR: This work extends multi-modal scene understanding to include that of free-hand scene sketches, and uniquely results in a trilogy of scene data modalities (sketch, text, and photo), where each offers unique perspectives for scene understanding, and together enable a series of novel scene-specific applications across discriminative and generative tasks.
Journal ArticleDOI
A Subspace Projection Approach to Autoencoder-based Anomaly Detection
TL;DR: In this paper , the authors propose a framework of AE-based anomaly detection, coined HFR-AE, by projecting new inputs into a subspace wherein the trained AE achieves high-fidelity reconstruction, thereby increasing the gap between normal and anomalous sample reconstruction errors.
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.