In this paper a model of neural unit that take into account the effect of mean time decay output ("stress") observed in the Hodgkin-Huxley model is presented. A simplified version of the stress effect is implemented in a static neuron element by means of a dynamical threshold. A rule to vary the threshold adopting local information is then presented and the effects of this law over the learning are examined in the class of standard competitive learning rule. The properties of stability of this model are examined and it is shown that the proposed unit, under appropriate hypothesis, 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 (feature).
Dynamical Threshold for a feature detector Neural Model / Chiarantoni, E.; Fornarelli, G.; Vacca, F.; Vergura, S.. - STAMPA. - (2001), pp. 28-31. (Intervento presentato al convegno International Joint Conference on Neural Networks, IJCNN'01 tenutosi a Washington, DC nel July 15-19, 2001) [10.1109/IJCNN.2001.938986].
Dynamical Threshold for a feature detector Neural Model
E. Chiarantoni;G. Fornarelli;F. Vacca;S. Vergura
2001-01-01
Abstract
In this paper a model of neural unit that take into account the effect of mean time decay output ("stress") observed in the Hodgkin-Huxley model is presented. A simplified version of the stress effect is implemented in a static neuron element by means of a dynamical threshold. A rule to vary the threshold adopting local information is then presented and the effects of this law over the learning are examined in the class of standard competitive learning rule. The properties of stability of this model are examined and it is shown that the proposed unit, under appropriate hypothesis, 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 (feature).I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
