Training of a feedforward multiple-valued neural network by error backpropagation with a multilevel threshold function

A technique for the training of multiple-valued neural networks based on a backpropagation learning algorithm employing a multilevel threshold function is proposed. The optimum threshold width of the multilevel function and the range of the learning parameter to be chosen for convergence are derived. Trials performed on a benchmark problem demonstrate the convergence of the network within the specified range of parameters.

[1]  Masayuki Matsumoto,et al.  A design of multiple-valued logic neuron , 1990, Proceedings of the Twentieth International Symposium on Multiple-Valued Logic.

[2]  Robert W. Newcomb,et al.  Circuits for multi-level neuron nonlinearities , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[3]  Vijayan K. Asari,et al.  A supervised learning neural network for self-organized mapping of multiple-valued patterns , 1999, Neural Parallel Sci. Comput..

[4]  Hiroki Matsumoto,et al.  Algorithm and implementation of a learning multiple-valued logic network , 1993, [1993] Proceedings of the Twenty-Third International Symposium on Multiple-Valued Logic.

[5]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[6]  Chikkannan Eswaran,et al.  Bidirectional multiple‐valued neural network for pattern recognition and associative recall , 2000 .

[7]  Ivan Stojmenovic,et al.  STRIP - a strip-based neural-network growth algorithm for learning multiple-valued functions , 2001, IEEE Trans. Neural Networks.