Cumulative inhibition in neural networks

Forskningsoutput: TidskriftsbidragArtikel i vetenskaplig tidskrift

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.

Detaljer

Författare
Enheter & grupper
Forskningsområden

Ämnesklassifikation (UKÄ) – OBLIGATORISK

  • Jämförande språkvetenskap och lingvistik

Nyckelord

Originalspråkengelska
TidskriftCognitive Processing
StatusE-pub ahead of print - 2018 nov 3
PublikationskategoriForskning
Peer review utfördJa

Related projects

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

2018/11/01 → …

Projekt: Nätverk

Visa alla (2)

Relaterad infrastruktur

Visa alla (1)