Sparse Distributed Memory Mapping on Partial Tree Shape Neurocomputer

Abstract

Mapping of Kanerva’s Sparse Distributed Memory (SDM) is presented for a partial tree shape neurocomputer. We discuss the original model and give a detailed parallel mapping for improved SDM models, using Karlsson’s activation mechanism and efficient reading methods. Both row-wise and column-wise mappings can be effectively used, but column-wise mapping is analysed in more details because it minimizes communication in the improved read operation. Instead, rowwise mapping parallelized the activation mechanism so that it is better in slower activation methods or when needed a very fast writing procedure. Performance analysis deals with SDM matrix sizes, memory capacity and load balance.KeywordsLoad BalanceField Programmable Gate ArrayMemory CapacityMemory ItemRead OperationThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.