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
What-Is and How-To for Fairness in Machine Learning: A Survey, Reflection, and Perspective
Zeyu Tang,Jiji Zhang,Kun Zhang +2 more
TL;DR: It is demonstrated the importance of matching the mission and the means of different types of fairness inquiries on the data generating process, on the predicted outcome, and on the induced impact, respectively, to achieve the intended purpose.
Journal ArticleDOI
S3-VAE: A novel Supervised-Source-Separation Variational AutoEncoder algorithm to discriminate tumor cell lines in time-lapse microscopy images
Paola Casti,Sara Cardarelli,Maria Colomba Comes,Maria D’Orazio,Joanna Filippi,G. Antonelli,Arianna Mencattini,Corrrado Di Natale,Emiliano Martinelli +8 more
TL;DR: In this paper , a Supervised-Source-Separation Variational Autoencoder (S3-VAE) is proposed to guide the encoding process of images toward a more effective class-separability.
Posted Content
Learning Disentangled Representations for Time Series.
TL;DR: In this article, a disentanglement enhancement framework for sequential data is proposed to generate hierarchical semantic concepts as the interpretable and disentangled representation of time-series, which can be used for downstream applications.
Journal ArticleDOI
Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck
TL;DR: In this paper , an adversarial threat model under a mutual information constraint is considered to cover a wider class of perturbations in training. And the authors propose an autoencoder-based training to implement the objective, as well as practical encoder designs to facilitate the proposed hybrid discriminative-generative training concerning both convolutional and transformer-based architectures.
Relaxing the Kolmogorov Structure Function for Realistic Computational Constraints
TL;DR: Xu et al. as discussed by the authors incorporate computational constraints into measures of information by assuming that the compressor belongs to a fixed family of predictive functions, which may not show the complete story about the information inside data because different aspects of the data become decodable at different scales of computation.
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.