A VLSI optimal constructive algorithm for classification problems
Valeriu C. Beiu, Sorin Drăghici, Ishwar K. Sethi · University of North Texas Digital Library (University of North Texas) · 1997
If neural networks are to be used on a large scale, they have to be implemented in hardware. However, the cost of the hardware implementation is critically sensitive to factors like the precision used for the weights, the total number of bits of information and the maximum fan-in used in the network. This paper presents a version of the Constraint Based Decomposition training algorithm which is able to produce networks using limited precision integer weights and units with limited fan-in. The algorithm is tested on the 2-spiral problem and the results are compared with other existing algorithms.