In this paper some considerations are developed to design a neural unit that takes into account a number of biological effects, namely a fluctuating threshold for the activation of the unit and a learning law dependent on the past history of the unit. The properties of this new neural unit are examined and it is shown how this unit is able to find autonomously (i.e. without requiring any interaction with other units) a local maximum of density in the input data set space.
Modelling fatigue and dynamic learning in a self-organizing neural cell model / Acciani, G.; Chiarantoni, E.; Minenna, M.. - STAMPA. - (1996), pp. 609-612. (Intervento presentato al convegno 8th Mediterranean Electrotechnical Conference on Industrial Applications in Power Systems, Computer Science and Telecommunications, MELECON 96 tenutosi a Bari, Italy nel May 13-16, 1996) [10.1109/MELCON.1996.551294].
Modelling fatigue and dynamic learning in a self-organizing neural cell model
G. Acciani;E. Chiarantoni;
1996-01-01
Abstract
In this paper some considerations are developed to design a neural unit that takes into account a number of biological effects, namely a fluctuating threshold for the activation of the unit and a learning law dependent on the past history of the unit. The properties of this new neural unit are examined and it is shown how this unit is able to find autonomously (i.e. without requiring any interaction with other units) a local maximum of density in the input data set space.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
