Neural Network Capacity for Multilevel Inputs
This work addresses memory limitations in neural networks, offering incremental improvements for applications requiring enhanced pattern storage and retrieval.
The paper tackles the problem of limited memory capacity in Hopfield networks by introducing multilevel inputs and new learning strategies, resulting in significantly increased capacity and enabling recall of entire patterns from single-neuron stimulation.
This paper examines the memory capacity of generalized neural networks. Hopfield networks trained with a variety of learning techniques are investigated for their capacity both for binary and non-binary alphabets. It is shown that the capacity can be much increased when multilevel inputs are used. New learning strategies are proposed to increase Hopfield network capacity, and the scalability of these methods is also examined in respect to size of the network. The ability to recall entire patterns from stimulation of a single neuron is examined for the increased capacity networks.