Linear quantization of Hebbian-type associative memories in interconnection implementations

The effects of linear quantized Hebbian-type associative memories (HAMs) on storage capacity and hardware implementations are explored in this paper. For the linear quantization, the interconnection weights are linearly quantized into a small number of levels. This consideration focuses mainly on the situation when only a limited accuracy range can be achieved on hardware implementations. Results of simulation and theory show that the number of quantization levels required is relatively small compared with the possible values of interconnections. Therefore, linear quantization in HAMs is worthwhile in hardware implementations