In this paper, we propose a fast winner-take-all (WTA) neural network by dynamically accelerating the mutual inhibition among competitive neurons. The highest-threshold neural network (HITNET) with an accelerated factor is evolved from the general mean-based neural network (GEMNET), which adopts the mean of active neurons as the threshold of mutual inhibition. When the accelerated factor is optimally designed, the ideal HITNET statistically achieves the highest threshold for mutual inhibition. Both theoretical analyzes and simulation results demonstrate that the practical HITNET converges faster than the existing WTA networks for a large number of competitors.
All Science Journal Classification (ASJC) codes
- Computer Science Applications
- Computer Networks and Communications
- Artificial Intelligence