论文信息 - A study of various desired response and error scaling sequences for temporal pattern classification using a FIR neural network

A study of various desired response and error scaling sequences for temporal pattern classification using a FIR neural network

A finite impulse response neural network is configured to act as a temporal pattern classifier. The notion of desired response and error scaling sequences is introduced and the effects of these sequences on the classification rate and network outputs is examined. Narrow error scaling functions speed learning but produce poor quality outputs. Wide error scaling functions produce better quality output but learn more slowly.

M. Stevenson | N. Arsenault

[1] R.N. Scott,et al. A new strategy for multifunction myoelectric control , 1993, IEEE Transactions on Biomedical Engineering.

[2] Thomas L. Hemminger,et al. Detection and classification of underwater acoustic transients using neural networks , 1994, IEEE Trans. Neural Networks.

[3] Eric A. Wan,et al. Finite impulse response neural networks with applications in time series prediction , 1994 .

[4] Geoffrey E. Hinton,et al. Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..