Deep learning and the information bottleneck principle

N Tishby, N Zaslavsky - 2015 ieee information theory workshop …, 2015 - ieeexplore.ieee.org
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 …

Nonlinear information bottleneck

A Kolchinsky, BD Tracey, DH Wolpert - Entropy, 2019 - mdpi.com
Information bottleneck (IB) is a technique for extracting information in one random variable X
that is relevant for predicting another random variable Y. IB works by encoding X in a …

An ensemble approach of feature selection and machine learning models for regional landslide susceptibility mapping in the arid mountainous terrain of Southern …

C Kumar, G Walton, P Santi, C Luza - Remote Sensing, 2023 - mdpi.com
This study evaluates the utility of the ensemble framework of feature selection and machine
learning (ML) models for regional landslide susceptibility mapping (LSM) in the arid climatic …

Information bottleneck for Gaussian variables

G Chechik, A Globerson, N Tishby… - Advances in Neural …, 2003 - proceedings.neurips.cc
The problem of extracting the relevant aspects of data was addressed through the
information bottleneck (IB) method, by (soft) clustering one variable while preserving …

Learning and generalization with the information bottleneck

O Shamir, S Sabato, N Tishby - Theoretical Computer Science, 2010 - Elsevier
The Information Bottleneck is an information theoretic framework that finds concise
representations for an 'input'random variable that are as relevant as possible for an …

On the information bottleneck problems: Models, connections, applications and information theoretic views

A Zaidi, I Estella-Aguerri, S Shamai - Entropy, 2020 - mdpi.com
This tutorial paper focuses on the variants of the bottleneck problem taking an information
theoretic perspective and discusses practical methods to solve it, as well as its connection to …

Brain more resistant to energy restriction than body: a systematic review

M Sprengell, B Kubera, A Peters - Frontiers in Neuroscience, 2021 - frontiersin.org
The gluco-lipostatic theory and its modern variants assume that blood glucose and energy
stores are controlled in closed-loop feedback processes. The Selfish Brain theory is based …

Task-oriented communication design in cyber-physical systems: A survey on theory and applications

A Mostaani, TX Vu, SK Sharma, VD Nguyen… - IEEE …, 2022 - ieeexplore.ieee.org
Communication system design has been traditionally guided by task-agnostic principles,
which aim at efficiently transmitting as many correct bits as possible through a given …

Multiterminal source coding under logarithmic loss

TA Courtade, T Weissman - IEEE Transactions on Information …, 2013 - ieeexplore.ieee.org
We consider the classical two-encoder multiterminal source coding problem where distortion
is measured under logarithmic loss. We provide a single-letter description of the achievable …

Caveats for information bottleneck in deterministic scenarios

A Kolchinsky, BD Tracey, S Van Kuyk - arXiv preprint arXiv:1808.07593, 2018 - arxiv.org
Information bottleneck (IB) is a method for extracting information from one random variable $
X $ that is relevant for predicting another random variable $ Y $. To do so, IB identifies an …