In this paper, sparsely-connected neural networks synthesized for recognizing discrete-time sinusoidal signals as a possible support in children’s acoustic rehabilitation are considered. In particular, a robustness analysis of this kind of sparsely-connected neural networks is developed, both in the presence of perturbed input patterns and of network parameter variations. Performances are evaluated by choosing simple acoustic signals, that is, sinusoidal signals with different values of angular frequency, width and phase. Test cases are reported to illustrate the capabilities of designed networks
On Performances of Sparsely-Connected Neural Networks for Acoustic Signal Recognition / Carnimeo, Leonarda; Giaquinto, Antonio. - In: WSEAS TRANSACTIONS ON INFORMATION SCIENCE AND APPLICATIONS. - ISSN 1790-0832. - STAMPA. - 1:6(2004), pp. 1743-1746.
On Performances of Sparsely-Connected Neural Networks for Acoustic Signal Recognition
Leonarda Carnimeo;Antonio Giaquinto
2004-01-01
Abstract
In this paper, sparsely-connected neural networks synthesized for recognizing discrete-time sinusoidal signals as a possible support in children’s acoustic rehabilitation are considered. In particular, a robustness analysis of this kind of sparsely-connected neural networks is developed, both in the presence of perturbed input patterns and of network parameter variations. Performances are evaluated by choosing simple acoustic signals, that is, sinusoidal signals with different values of angular frequency, width and phase. Test cases are reported to illustrate the capabilities of designed networksI documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
