Back-propagation algorithm which varies the number of hidden units
Generate an AI Snapshot to get a quick, structured summary of this paper.
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This algorithm is expected to escape local minima and makes it no longer necessary to decide the number of hidden units, and it is shown that in alphanumeric font learning, the network converged two to three times faster than conventional back-propagation.
Abstract
This report presents a back-propagation algorithm that varies the number of hidden units. This algorithm is expected to escape local minima and makes it no longer necessary to decide the number of hidden units. We tested this algorithm on two examples. One was exclusive-OR learning and the other was 8 × 8 dot alphanumeric font learning. In both examples, the probability of becoming trapped in local minima was reduced. Furthermore, in alphanumeric font learning, the network converged two to three times faster than conventional back-propagation.