Part of Advances in Neural Information Processing Systems 2 (NIPS 1989)
The effects of parameter modifications imposed by hardware con(cid:173) straints on a self-organizing feature map algorithm were examined. Performance was measured by the error rate of a speech recogni(cid:173) tion system which included this algorithm as part of the front-end processing. System parameters which were varied included weight (connection strength) quantization, adap tation quantization, dis(cid:173) tance measures and circuit approximations which include device characteristics and process variability. Experiments using the TI isolated word database for 16 speakers demonstrated degradation in performance when weight quantization fell below 8 bits. The com(cid:173) petitive nature of the algorithm rela..xes constraints on uniformity and linearity which makes it an excellent candidate for a fully ana(cid:173) log circuit implementation. Prototype circuits have been fabricated and characterized following the constraints established through the simulation efforts.