Analogue Imprecision in Mlp Training, Progress in Neural Processing, Vol 4

ISBN-13: 9789810227395 / Angielski / Twarda / 1996 / 192 str.

Peter J. Edwards; Alan F. Murray

Opis

Hardware inaccuracy and imprecision are important factors when implementing neural algorithms. This text presents a study of synaptic weight noise as a typical fault model for analogue VLSI realizations of MLP neural networks, and examines the implications for learning and network performance.