摘要
This paper first establishes a neural network model for logic circuits fromthe truth table by using linear equations theory, presents a kind of ATPG neuralnetwork model, and investigates energy local minima for the network- And then,it proposes the corresponding techniques to reduce the number of energy localminima as well as some approaches to escaping from local minimum of eliergyFinally, two simulation systems, the binary ATPG neural network and thecontinuous ATPG neural network, are implemented oli SUN 3/260 workstationin C language. The experimental results and their analysis and discussion aregiven. The preliminary experimental results show that this method is feasibleand promising.
This paper first establishes a neural network model for logic circuits fromthe truth table by using linear equations theory, presents a kind of ATPG neuralnetwork model, and investigates energy local minima for the network- And then,it proposes the corresponding techniques to reduce the number of energy localminima as well as some approaches to escaping from local minimum of eliergyFinally, two simulation systems, the binary ATPG neural network and thecontinuous ATPG neural network, are implemented oli SUN 3/260 workstationin C language. The experimental results and their analysis and discussion aregiven. The preliminary experimental results show that this method is feasibleand promising.
