Page Content
Conference Publications
| Citation key | Weber1999 |
|---|---|
| Author | Weber, C. and Obermayer, K. |
| Title of Book | Artificial Neural Networks - ICANN 99 |
| Pages | 286 – 291 |
| Year | 1999 |
| ISBN | 0-85296-721-7 |
| ISSN | 0537-9989 |
| DOI | 10.1049/cp:19991123 |
| Volume | 1 |
| Publisher | IEEE |
| Abstract | In our contribution we investigate a sparse coded Boltzmann machine as a model for the formation of orientation selective receptive fields in primary visual cortex. The model consists of two layers of neurons which are recurrently connected and which represent the lateral geniculate nucleus and primary visual cortex. Neurons have ternary activity values $+1$, $-1$, and $0$, where the $0$-state is degenerate being assumed with higher prior probability. The probability for a (stochastic) activation vector on the net obeys the Boltzmann distribution and maximum-likelihood leads to the standard Boltzmann learning rule. We apply a mean-field version of this model to natural image processing and find that neurons develop localized and oriented receptive fields. |
Back [4]
/webe99c_sparseBM.ps.gz
eload=true&arnumber=819735
ls_of_neural_systems/conference_publications/parameter/
en/minhilfe/?no_cache=1&tx_sibibtex_pi1%5Bdownload_
bibtex_uid%5D=1166786&tx_sibibtex_pi1%5Bcontentelem
ent%5D=tt_content%3A310688
ls_of_neural_systems/conference_publications/parameter/
en/minhilfe/
Zusatzinformationen / Extras
Quick Access:
Schnellnavigation zur Seite über Nummerneingabe
Auxiliary Functions
Copyright TU Berlin 2008