Patent
1991-07-10
1992-07-07
MacDonald, Allen R.
G06F 1518
Patent
active
051290391
ABSTRACT:
The present invention is concerned with a signal processing system having a learning function pursuant to the back-propagation learning rule by the neural network, in which the learning rate is dynamically changed as a function of input values to effect high-speed stable learning. The signal processing system of the present invention is so arranged that, by executing signal processing for the input signals by the recurrent network formed by units each corresponding to a neuron, the features of the sequential time series pattern such as voice signals fluctuating on the time axis can be extracted through learning the coupling state of the recurrent network. The present invention is also concerned with a learning processing system adapted to cause the signal processing section formed by a neural network to undergo signal processing pursuant to the back-propagation learning rule, wherein the local minimum state in the course of the learning processing may be avoided by learning the coefficient of coupling strength while simultaneously increasing the number of the unit of the intermediate layer.
REFERENCES:
Neural Net Pruning--Why and How; Sietsma et al.; Proceedings of IEEE Int. Conf. on Neural Networks; vol. I; pp. 325-333; 1988.
Eslinger Lewis H.
MacDonald Allen R.
Maioli Jay H.
Sony Corporation
LandOfFree
Recurrent neural network with variable size intermediate layer does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Recurrent neural network with variable size intermediate layer, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Recurrent neural network with variable size intermediate layer will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1836139