Successive Refinement and Coarsening of the Information Bottleneck

Research output: Contribution to conferencePaperpeer-review

24 Downloads (Pure)

Abstract

We study two central aspects of information processing in cognitive systems: one is the ability to incorporate fresh information to already learnt models; the other is the “trickling” of information through the many layers of a cognitive processing pipeline. We investigate the extent to which these specific structures of cognitive processing impact their informational optimal limits. To do so, we present mathematical characterisations and low-dimensional numerical examples, which explore formal properties of the Information Bottleneck method: namely, how it relates to successive refinement, and successive coarsening of information.
Original languageEnglish
Pages1-8
Number of pages8
Publication statusPublished - 21 Nov 2022
EventNeurIPS 2022 Workshop on Information-Theoretic Principles in Cognitive Systems - New Orleans Convention Center, New Orleans, United States
Duration: 3 Dec 20223 Dec 2022
Conference number: 1
https://sites.google.com/view/infocog-neurips2022/home

Workshop

WorkshopNeurIPS 2022 Workshop on Information-Theoretic Principles in Cognitive Systems
Abbreviated titleNeurIPS 2022
Country/TerritoryUnited States
CityNew Orleans
Period3/12/223/12/22
Internet address

Keywords

  • Incremental learning
  • Information Bottleneck
  • Successive Refinement

Fingerprint

Dive into the research topics of 'Successive Refinement and Coarsening of the Information Bottleneck'. Together they form a unique fingerprint.

Cite this