Acquiring rules of selecting cells by using neural network

This paper describes the way to express the rules of selecting cells in logic synthesis and the acquisition of these rules based on neural networks. The trained neural network can be used to finish the selection of cells. Using neural networks in logic synthesis based on standard cell library can achieve the goal that the algorithm of technology mapping is independent of the cell library and the corresponding set of rules of selecting those cells in the library. The application of neural networks in the selection of cells can avoid the `combinational explosion'' of the search space.© (1991) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.