Abstract
This paper describes a neural network with lateral inhibition, which exhibits dynamic winner-take-all (WTA) behavior. The equations of this network model a current input MOSFET WTA circuit, which motivates the discussion. A very general sufficient condition for the network to have a WTA equilibrium point is obtained and sufficient conditions for the network to converge to the WTA point are presented. This gives explicit expressions for tire resolution and lower bound of the input currents. We also show that whenever the network gets into the WTA region, it will stay in that region and settle down exponentially fast to the WTA point. This provides a speed up procedure for the decision making. as soon as it gets into the region, the winner can be picked up. Finally, we show that this WTA neural network has a self-resetting property.
| Original language | English |
|---|---|
| Pages (from-to) | 1141-1154 |
| Journal | Neural Networks |
| Volume | 9 |
| Issue number | 7 |
| DOIs | |
| Publication status | Published - Oct 1996 |
| Externally published | Yes |
Bibliographical note
Publication details (e.g. title, author(s), publication statuses and dates) are captured on an “AS IS” and “AS AVAILABLE” basis at the time of record harvesting from the data source. Suggestions for further amendments or supplementary information can be sent to [email protected].Research Keywords
- Competition
- Lateral inhibition
- MOSFET
- Nonlinear dynamics
- Shunting inhibition
- VLSI neural networks
- Winnter-take-all