Büddefeld, J.J.BüddefeldGroßpietsch, K.-E.K.-E.Großpietsch2022-03-032022-03-032002https://publica.fraunhofer.de/handle/publica/20294810.1109/MM.2002.1013302Execution of artificial neural nets, especially for online pattern recognition, mainly depends on time efficient execution of weighted sums. In this paper, a new architecture for achieving this goal is presented. This architecture uses additional logic to extend the functionality of conventional RAM. It is shown that its computation performance is superior to the time complexity of sequential von Neuman machines.enassociative processor systemartificial neural network005006629004Intelligent-memory architecture for artificial neural networksjournal article