ar X iv : c om p - ga s / 94 08 00 1 v 1 2 6 A ug 1 99 4 Recognition of Temporal Sequences of Patterns Using State - dependent Synapses
نویسندگان
چکیده
Using an asymmetric associative network with synchronous updating, it is possible to recall a sequence of patterns. To obtain a stable sequence generation with a large storage capacity, we introduce a threshold that eliminates the contribution of weakly correlated patterns. For this system we find a set of evolution equations for the overlaps of the states with the patterns to be recognized. We solve these equations in the limit of the stationary cycle, and obtain the critical value of the capacity as a function of the threshold and temperature. Finally, a numerical simulation is made, confirming the theoretical results. by the Association Générale pour la Coopération et le Développement (Belgium).
منابع مشابه
ar X iv : c s / 99 08 00 6 v 1 [ cs . C G ] 1 1 A ug 1 99 9 Computational Geometry Column 36
Two results in “computational origami” are illustrated. Computational geometry has recently been applied to solve two open problems in “origami mathematics.”
متن کاملar X iv : h ep - p h / 06 08 05 0 v 1 4 A ug 2 00 6 Percolation and high energy cosmic rays above 10 17 eV
متن کامل