Prototyping of WTA ANNs Using FPAA Devices

K. Wawryn, R. Suszyński (Koszalin Univ. of Techn., Poland)

A rapid prototyping method for designing a winner takes all (WTA) artificial neural networks (ANNs) has been presented in the paper. The method is based on implementation of field programmable analog arrays (FPAAs) to design WTA ANNs. Programmable synaptic weight connection circuit and 2-WTA circuit are proposed. The 2-WTA circuits are used to configure 4-WTA and 8-WTA circuits. 4-WTA and 8-WTA circuits and programmable synaptic weight connection circuit have been implemented in FPAA device, simulated with a help of the Matlab software and finally measured. Measured characteristics have been compared to simulated ones.