Issue No. 12 - December (1991 vol. 40)

ISSN: 0018-9340

pp: 1402-1412

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/12.106225

ABSTRACT

<p>The tradeoffs between the depth (i.e., the time for parallel computation) and the size (i.e., the number of threshold gates) in neural networks are studied. The authors focus the study on the neural computations of symmetric Boolean functions and some arithmetic functions. It is shown that a significant reduction in the size is possible for symmetric functions and some arithmetic functions, at the expense of a small constant increase in depth. In the process, several neural networks which have the minimum size among all the known constructions have been developed. Results on implementing symmetric functions can be used to improve results about arbitrary Boolean functions. In particular, it is shown that any Boolean function can be computed in a depth-3 neural network with O(2/sup n/ /sup 2/) threshold gates; it is also proven that at least Omega (2/sup n/ /sup 3/) threshold gates are required.</p>

INDEX TERMS

neural computation; parallel computation; size; threshold gates; symmetric Boolean functions; arithmetic functions; depth-3; Boolean functions; neural nets; threshold logic.

CITATION

V.P. Roychowdhury, K.Y. Siu, T. Kailath, "Depth-Size Tradeoffs for Neural Computation",

*IEEE Transactions on Computers*, vol. 40, no. , pp. 1402-1412, December 1991, doi:10.1109/12.106225