Cumulative inhibition in neural networks

Forskningsoutput: TidskriftsbidragArtikel i vetenskaplig tidskriftPeer review

4 Citeringar (SciVal)

Sammanfattning

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.
Originalspråkengelska
Sidor (från-till)87-102
TidskriftCognitive Processing
Volym20
Utgåva1
Tidigt onlinedatum2018 nov. 3
DOI
StatusPublished - 2019

Ämnesklassifikation (UKÄ)

  • Jämförande språkvetenskap och lingvistik

Fingeravtryck

Utforska forskningsämnen för ”Cumulative inhibition in neural networks”. Tillsammans bildar de ett unikt fingeravtryck.

Citera det här