Speech and Vision Lab

  • Increase font size
  • Default font size
  • Decrease font size
Home Publications
Backpropagation learning algorithms for classification with fuzzy mean square error
Research Area: Uncategorized Year: 1998
Type of Publication: Article Keywords: Crisp classification; Fuzzy classification; Possibilistic classification; Neural networks and backpropagation
Authors: Manish Sarkar, B. Yegnanarayana, Deepak Khemani  
Most of the real life classification problems have ill defined, imprecise or fuzzy class boundaries. Feedforward neural networks with conventional backpropagation learning algorithm are not tailored to this kind of classification problem. Hence, in this paper, feedforward neural networks, that use backpropagation learning algorithm with fuzzy objective functions, are investigated. A learning algorithm is proposed that minimizes an error term, which reflects the fuzzy classification from the point of view of possibilistic approach. Since the proposed algorithm has possibilistic classification ability, it can encompass different backpropagation learning algorithm based on crisp and constrained fuzzy classification. The efficacy of the proposed scheme is demonstrated on a vowel classification problem.
Digital version