Training Winner-Take-All Simultaneous Recurrent Neural Networks
This document has been relocated to http://scholarsmine.mst.edu/ele_comeng_facwork/1311
There were 30 downloads as of 27 Jun 2016.
Abstract
The winner-take-all (WTA) network is useful in database management, very large scale integration (VLSI) design, and digital processing. The synthesis procedure of WTA on single-layer fully connected architecture with sigmoid transfer function is still not fully explored. We discuss the use of simultaneous recurrent networks (SRNs) trained by Kalman filter algorithms for the task of finding the maximum among N numbers. The simulation demonstrates the effectiveness of our training approach under conditions of a shared-weight SRN architecture. A more general SRN also succeeds in solving a real classification application on car engine data.
