Cumulative inhibition in neural networks

Research output: Contribution to journalArticle

Abstract

We show how a multi-resolution network can model the development of acuity and coarse-to-fine processing in the mammalian visual cortex. The network adapts to input statistics in an unsupervised manner, and learns a coarse-to-fine representation by using cumulative inhibition of nodes within a network layer. We show that a system of such layers can represent input by hierarchically composing larger parts from smaller components. It can also model aspects of top-down processes, such as image regeneration.

Details

Authors
Organisations
Research areas and keywords

Subject classification (UKÄ) – MANDATORY

  • General Language Studies and Linguistics

Keywords

  • Cumulative inhibition, Multi-resolution, Coarse-to-fine processing, Unsupervised learning, Acuity, Cortical microcolumn, Visual cortex
Original languageEnglish
Pages (from-to)87-102
JournalCognitive Processing
Volume20
Issue number1
Early online date2018 Nov 3
Publication statusPublished - 2019
Publication categoryResearch
Peer-reviewedYes

Related projects

Andreas Stephens, Trond Arild Tjöstheim, Maximilian Roszko, Erik J Olsson, Andrey Anikin & Theoretical Philosophy, University of Zurich Arthur Schwaninger

2018/11/01 → …

Project: Network

View all (2)