A Hebbian/Anti-Hebbian network derived from online non-negative matrix factorization can cluster and discover sparse features.

janelia7_blocks-janelia7_biblio_header | block

2014 48th Asilomar Conference on Signals, Systems and Computers2014 48th Asilomar Conference on Signals, Systems and Computers. 2015 Mar 02;. doi: 10.1109/ACSSC.2014.7094553

Pehlevan C, Chklovskii DB

janelia7_blocks-janelia7_biblio_abstract | block

Abstract

Olshausen and Field (OF) proposed that neural computations in the primary visual cortex (V1) can be partially modelled by sparse dictionary learning. By minimizing the regularized representation error they derived an online algorithm, which learns Gabor-filter receptive fields from a natural image ensemble in agreement with physiological experiments. Whereas the OF algorithm can be mapped onto the dynamics and synaptic plasticity in a single-layer neural network, the derived learning rule is nonlocal - the synaptic weight update depends on the activity of neurons other than just pre- and postsynaptic ones – and hence biologically implausible. Here, to overcome this problem, we derive sparse dictionary learning from a novel cost-function - a regularized error of the symmetric factorization of the input’s similarity matrix. Our algorithm maps onto a neural network of the same architecture as OF but using only biologically plausible local learning rules. When trained on natural images our network learns Gabor-filter receptive fields and reproduces the correlation among synaptic weights hard-wired in the OF network. Therefore, online symmetric matrix factorization may serve as an algorithmic theory of neural computation.

node:body | entity_field

Main Menu (Mobile)- Block

Main Menu - Block

A Hebbian/Anti-Hebbian network derived from online non-negative matrix factorization can cluster and discover sparse features.

Abstract