Frederic M. Ham

We don’t have enough information about this author to calculate their statistics. If you think this is an error let us know.
Learn More
An algorithm to train feedforward multilayer perceptrons is presented. This algorithm trains the perceptron in fewer pattern presentations than standard backpropagation. A parallel processing scheme renders it computationally efficient. The algorithm uses the error backpropagated from the output layer to each node in the network to formulate a normal(More)
  • 1