SELF-ORGANIZING NETWORK FOR FEATURE-MAP FORMATION - ANALOG INTEGRATED-CIRCUIT ROBUST TO DEVICE AND CIRCUIT MISMATCH

A network model self-organizing a feature map was proposed and investi gated in computer simulations as well as experiments. The network was quite effective for self-organizing a feature map, in which winner gro ups are formed with redundant neurons. Fundamental circuits for the se lf-organizing network were developed. The experimental results were in good agreement with results of SPICE simulation. It was verified in a primitive network that feature maps were self-organized with high pro bability for 9 input patterns. It was clarified that redundant neurons forming a winner group are a key for solving a problem of wrong opera tion in analog circuits caused by the device and circuit mismatch. (C) 1998 Elsevier Science Ltd. All rights reserved.