Differential Learning Algorithm for Artificial Neural Networks

Free registration required

Executive Summary

Artificial Neural Networks (ANN) is extremely useful to relate the nonlinearly depending outputs with the inputs. Various architectures are available for the ANNs to speed up the training period and reduce the square error. In this paper, new classes of neural networks with differential feedback are presented. The different orders of differential feedback form a manifold of hyperplanes. Interesting properties of this Differentially fed ANN (DANN) are derived through these hyperplanes. Neural networks are generally used when the input and output of a system are non-linearly related.

  • Format: PDF
  • Size: 175.08 KB