Effective learning in recurrent max-min neural networks

  title={Effective learning in recurrent max-min neural networks},
  author={Loo-Nin Teow and Kia-Fock Loe},
  journal={Neural networks : the official journal of the International Neural Network Society},
  volume={11 3},
Max and min operations have interesting properties that facilitate the exchange of information between the symbolic and real-valued domains. As such, neural networks that employ max-min activation functions have been a subject of interest in recent years. Since max-min functions are not strictly differentiable, we propose a mathematically sound learning method based on using Fourier convergence analysis of side-derivatives to derive a gradient descent technique for max-min error functions. We… CONTINUE READING