Abstract
Consideration is given to switched linear resistive networks and nonlinear resistive networks for image smoothing and segmentation problems in robot vision. The latter network type is derived from the former by way of an intermediate stochastic formulation, and a new result relating the solution sets of the two is given for the so-called zero-temperature limit. The authors present simulation studies of several continuation methods that can be gracefully implemented in analog VLSI and that seem to given good results for these nonconvex optimization problems.
| Original language | British English |
|---|---|
| Pages (from-to) | 272-279 |
| Number of pages | 8 |
| Journal | Proceedings of the IEEE Conference on Decision and Control |
| Volume | 1 |
| State | Published - 1989 |
| Event | Proceedings of the 28th IEEE Conference on Decision and Control. Part 1 (of 3) - Tampa, FL, USA Duration: 13 Dec 1989 → 15 Dec 1989 |