---
title: "An Effective Learning Method for Max-Min Neural Networks"
authors:
  - "Loo-Nin Teow"
  - "Kia-Fock Loe"
doi: ""
url: "https://ijcai.org/proceedings/1997/164"
pdf: "https://ijcai.org/proceedings/1997/0164.pdf"
venue: "Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence"
year: 1997
pages: "1134-1138"
track: "Neural Networks"
keywords:
---

# An Effective Learning Method for Max-Min Neural Networks

Loo-Nin Teow, Kia-Fock Loe

*Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence*, pages 1134-1138.

## Abstract

Max and min operations have interesting properties that facilitate the exchange of information between the symbolic and real-v<~.lued 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. This method is applied to a "typical" fuzzy-neural network model employing max-min activation functions. We show how this network can be trained to perform function approximation; its performance was found to be better than that of a conventional feedforward neural network.