Matches in SemOpenAlex for { <https://semopenalex.org/work/W2552173600> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W2552173600 abstract "Following the work of citet{Olshausen98}, a number of unsupervised learning algorithms were proposed for receptive field formation in the primary visual cortex (V1). We describe here the theoretical formulation of a novel and simple algorithm aiming at achieving the shortest representation in an over-complete dictionary of unknown features using the L$_0$ norm, a NP-complete problem. Inspired by parallel computing solutions with spiking events, we propose here a solution based on correlation-based inhibition with a tuned egalitarian homeostasis. We present results of the simulation of this dynamical neural network with natural images and compare it to the {sc SparseNet} solution. This algorithm exhibited similarly the formation of edge-like components as is observed in the input layer of V1 and to assess the quality of the different sets of filters, we additionally compared their relative efficiencies and show that our sub-optimal solution to the hard problem performs better than the optimal solution to the relaxed problem. We also show that homeostasis, by tuning the competition and cooperation, may yield solutions of different qualities which coding efficiency drastically depended on the goal assigned to the model by the cost function. This model provides a bridge between the non-linearity of the neural response and optimal use of distributed probabilistic representations of information. It is suggesting the importance of the role of interactions within neural assemblies citep{Hebb49} to efficiently build representations in the neural code." @default.
- W2552173600 created "2016-11-30" @default.
- W2552173600 creator A5010769763 @default.
- W2552173600 date "2007-06-15" @default.
- W2552173600 modified "2023-09-27" @default.
- W2552173600 title "Sparse Hebbian Learning is efficient with egalitarian homeostasis" @default.
- W2552173600 hasPublicationYear "2007" @default.
- W2552173600 type Work @default.
- W2552173600 sameAs 2552173600 @default.
- W2552173600 citedByCount "0" @default.
- W2552173600 crossrefType "posted-content" @default.
- W2552173600 hasAuthorship W2552173600A5010769763 @default.
- W2552173600 hasConcept C111437709 @default.
- W2552173600 hasConcept C11413529 @default.
- W2552173600 hasConcept C154945302 @default.
- W2552173600 hasConcept C169760540 @default.
- W2552173600 hasConcept C17744445 @default.
- W2552173600 hasConcept C19071747 @default.
- W2552173600 hasConcept C199539241 @default.
- W2552173600 hasConcept C2776359362 @default.
- W2552173600 hasConcept C2779345533 @default.
- W2552173600 hasConcept C41008148 @default.
- W2552173600 hasConcept C49937458 @default.
- W2552173600 hasConcept C50644808 @default.
- W2552173600 hasConcept C77637269 @default.
- W2552173600 hasConcept C86803240 @default.
- W2552173600 hasConcept C94625758 @default.
- W2552173600 hasConceptScore W2552173600C111437709 @default.
- W2552173600 hasConceptScore W2552173600C11413529 @default.
- W2552173600 hasConceptScore W2552173600C154945302 @default.
- W2552173600 hasConceptScore W2552173600C169760540 @default.
- W2552173600 hasConceptScore W2552173600C17744445 @default.
- W2552173600 hasConceptScore W2552173600C19071747 @default.
- W2552173600 hasConceptScore W2552173600C199539241 @default.
- W2552173600 hasConceptScore W2552173600C2776359362 @default.
- W2552173600 hasConceptScore W2552173600C2779345533 @default.
- W2552173600 hasConceptScore W2552173600C41008148 @default.
- W2552173600 hasConceptScore W2552173600C49937458 @default.
- W2552173600 hasConceptScore W2552173600C50644808 @default.
- W2552173600 hasConceptScore W2552173600C77637269 @default.
- W2552173600 hasConceptScore W2552173600C86803240 @default.
- W2552173600 hasConceptScore W2552173600C94625758 @default.
- W2552173600 hasOpenAccess W2552173600 @default.
- W2552173600 hasRelatedWork W2039656002 @default.
- W2552173600 hasRelatedWork W2062690289 @default.
- W2552173600 hasRelatedWork W2153777646 @default.
- W2552173600 hasRelatedWork W2172308869 @default.
- W2552173600 hasRelatedWork W2772726705 @default.
- W2552173600 hasRelatedWork W2804606950 @default.
- W2552173600 hasRelatedWork W2808786382 @default.
- W2552173600 hasRelatedWork W2884938415 @default.
- W2552173600 hasRelatedWork W2897316208 @default.
- W2552173600 hasRelatedWork W2914461420 @default.
- W2552173600 hasRelatedWork W2963184208 @default.
- W2552173600 hasRelatedWork W2966626695 @default.
- W2552173600 hasRelatedWork W2969654366 @default.
- W2552173600 hasRelatedWork W3013380487 @default.
- W2552173600 hasRelatedWork W3084020051 @default.
- W2552173600 hasRelatedWork W3102303919 @default.
- W2552173600 hasRelatedWork W3105145799 @default.
- W2552173600 hasRelatedWork W3153348027 @default.
- W2552173600 hasRelatedWork W3208268610 @default.
- W2552173600 hasRelatedWork W3212458874 @default.
- W2552173600 isParatext "false" @default.
- W2552173600 isRetracted "false" @default.
- W2552173600 magId "2552173600" @default.
- W2552173600 workType "article" @default.