TY - GEN
T1 - Retrieval process of an associative memory with non-monotonic input-output function
AU - Nishimori, Hidetoshi
AU - Opris, Ioan
PY - 1993/1/1
Y1 - 1993/1/1
N2 - The retrieval process of an associative memory with a general input-output function is studied by means of a signal-to-noise ratio analysis. We derive a set of recursion relations for macroscopic variables to describe the time development of the network. By taking equilibrium limit of the recursion relations, we find that a certain type of non-monotonic input-output relation of a single neuron yields an enhanced memory capacity than the conventional monotonic relation. This result combined with Monte Carlo simulations confirms the prediction of Morita et al and reveals new aspects in the retrieval process.
AB - The retrieval process of an associative memory with a general input-output function is studied by means of a signal-to-noise ratio analysis. We derive a set of recursion relations for macroscopic variables to describe the time development of the network. By taking equilibrium limit of the recursion relations, we find that a certain type of non-monotonic input-output relation of a single neuron yields an enhanced memory capacity than the conventional monotonic relation. This result combined with Monte Carlo simulations confirms the prediction of Morita et al and reveals new aspects in the retrieval process.
UR - http://www.scopus.com/inward/record.url?scp=0027233203&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0027233203&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:0027233203
SN - 0780312007
T3 - 1993 IEEE International Conference on Neural Networks
SP - 353
EP - 358
BT - 1993 IEEE International Conference on Neural Networks
A2 - Anon, null
PB - Publ by IEEE
T2 - 1993 IEEE International Conference on Neural Networks
Y2 - 28 March 1993 through 1 April 1993
ER -