Turing machine simulation using hard-limiter neurons

We introduce a method for construction of a Turing machine using binary, hard-limiter neurons with integer weights and thresholds. We identify the problem of potentially infinite fan-in needed for read units. We give two approaches to tackle this problem. The first approach organizes the neural read units in the form of a pipeline. The second approach organizes the read units in tree-structure. We identify trade-off in time performance and design complexity for these two approaches.