On the state space of the binary neural network.

The authors discuss the case of deterministic known codewords for which storage is required and show that bounds on the retrieval probabilities and convergence rates can be achieved. The main tool which they use is birth-and-death Markov chains, describing the Hamming distance of the network's state from the stored patterns. The results are applicable to both the asynchronous network and to the Boltzmann machines and can be utilized to compare codeword sets in terms of efficiency of their retrieval when the neural network is used as a content addressable memory.