Neural network and method of using same
AssigneeMotorola, Inc.
InventorShay-Ping Thomas Wang
Life of this patent
Estimating the term…
Abstract
A neural network, which can be implemented either in hardware or software, is constructed of neurons or neuron circuits each having only one significant processing element in the form of a multiplier. The number of training examples is compared to the number of neurons in the neural network to effectuate training. The neural network utilizes a training algorithm which does not require repetitive training and which yields a global minimum to each given set of input vectors.
Claims20
A method for training a neural network comprising a plurality of neurons, said method for calculating weight values, said method comprising the following steps:
- (a) providing a plurality of training examples;
- (b) comparing the number of said training examples with the number of neurons in said neural network;
- (c) providing at least two techniques for calculating said weight values, wherein
- (i) if the number of neurons is equal to the number of training examples, using a matrix-inversion technique to solve for the value of each weight;
- (ii) if the number of neurons is not equal to the number of training examples, using a least-squares estimation technique to solve for the value of each weight.
Dependencies are inferred from the claim text.