On the Computational Complexity of Binary and Analog Symmetric Hopfield Nets

0403721 - UIVT-O 20000024 RIV US eng J - Článek v odborném periodiku
Šíma, Jiří - Orponen, P. - Antti-Poika, T.
On the Computational Complexity of Binary and Analog Symmetric Hopfield Nets.
Neural Computation. Roč. 12, č. 12 (2000), s. 2965-2989. ISSN 0899-7667. E-ISSN 1530-888X
Grant CEP: GA AV ČR IAB2030007
Výzkumný záměr: AV0Z1030915
Klíčová slova: Hopfield networks * computational power * convergence time * minimum energy problem * analog networks
Kód oboru RIV: BA - Obecná matematika
Impakt faktor: 2.702, rok: 2000

We investigate the computational properties of finite binary- and analogstate discrete-time symmetric Hopfield nets. For binary networks, we obtain a simulation of convergent symmetric networks by symmetric networks with only a linear increase in network size and computation time. Then we analyze the convergence time of Hopfield nets in terms of the length of their bit representations.
Trvalý link: http://hdl.handle.net/11104/0124015