论文信息 - Evolutionary strategy for learning multiple-valued logic functions

Evolutionary strategy for learning multiple-valued logic functions

We consider the problem of synthesizing multiple-valued logic functions by neural networks. An evolutionary strategy (ES) which finds the longest strip in V/spl sube/K/sup n/ is described. A strip contains points located between two parallel hyperplanes. Repeated application of ES partitions the space V into a certain number of strips, each of them corresponding to a hidden unit. We construct neural networks based on these hidden units. Preliminary experimental results are presented and discussed.

Ivan Stojmenovic | Alioune Ngom | Dan A. Simovici

[1] Ivan Stojmenovic,et al. Learning with Permutably Homogeneous Multiple-Valued Multiple-Threshold Perceptrons , 2004, Neural Processing Letters.

[2] Mario Marchand,et al. On learning simple neural concepts: from halfspace intersections to neural decision lists , 1993 .

[3] Marcus Frean,et al. The Upstart Algorithm: A Method for Constructing and Training Feedforward Neural Networks , 1990, Neural Computation.

[4] Ivan Stojmenovic,et al. Learning with permutably homogeneous multiple-valued multiple-threshold perceptrons , 1998, Proceedings. 1998 28th IEEE International Symposium on Multiple- Valued Logic (Cat. No.98CB36138).

[5] Tom Downs,et al. CARVE-a constructive algorithm for real-valued examples , 1998, IEEE Trans. Neural Networks.

[6] M. Golea,et al. A Convergence Theorem for Sequential Learning in Two-Layer Perceptrons , 1990 .

[7] John B. Shoven,et al. I , Edinburgh Medical and Surgical Journal.

[8] Ivan Stojmenovic,et al. On the number of multilinear partitions and the computing capacity of multiple-valued multiple-threshold perceptrons , 2003, IEEE Trans. Neural Networks.

[9] Ivan Stojmenovic,et al. Synthesis of multiple-valued logic functions by neural networks , 1998 .

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