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 Article
Self-Adaptive In-Context Learning: An Information Compression Perspective for In-Context Example Selection and Ordering
TL;DR: Li et al. as discussed by the authors proposed a self-adaptive in-context learning (SIL) method to help each sample find an incontext example organization (i.e., selection and permutation) that can derive the correct prediction, thus maximizing performance.
Posted Content
Deep Fundamental Factor Models.
Matthew Dixon,Nicholas G. Polson +1 more
TL;DR: This work assesses a 49 factor model and generates information ratios that are approximately 1.5x greater than the OLS factor model, and compares it with a quadratic LASSO model and demonstrates the superior performance and robustness to outliers.
Posted Content
Don't Overlook the Support Set: Towards Improving Generalization in Meta-learning.
TL;DR: A new meta-training strategy is produced that linearly combines the input and hidden representations of samples from both the support and query sets and obtains state-of-the-art results by a large margin across many datasets and remains compatible with existing meta-learning algorithms.
Journal ArticleDOI
Robust Architecture-Agnostic and Noise Resilient Training of Photonic Deep Learning Models
TL;DR: In this article , the authors propose a novel training method for photonic neuromorphic architectures that is capable of taking into account a wide range of limitations of the actual hardware, including noise sources and easily saturated activation mechanisms.
Posted Content
Hunting for Dark Matter Subhalos in Strong Gravitational Lensing with Neural Networks
TL;DR: In this article, deep neural networks are used to detect subhalos on the lensing arc of a smooth lens where there is no subhalo, and neural networks not only show promising results on detecting multiple sub-halos, but also learn to reject the sub-halo on the smooth lens.
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.