A neural network for 3-satisfiability problems
Chen, Hsieh · 1989
Summary form only given, as follows. Based on Hopfield's associative memory model, a scheme for solving 3-satisfiability (3-SAT) problems is proposed. For problems such as 3-SAT, the partial constraints are easy to determine, but the global constraint is hard to find. The neural network associative memory is viewed as some kind of active memory, which means that it does not just memorize data items, but also manipulates those stored data. The operations that it can perform can be considered as constraint satisfaction. Thus, it is possible to store partial assignments which satisfy the local constraints of the problem and let the memory compose complete assignments which satisfy the global constraints. Simulation results show that this scheme can solve most instances of 3-SAT.>