Abstract
We derive cooling schedules for the global optimization of learning in neural networks. We discuss a two-level system with one global and one local minimum. The analysis is extended to systems with many minima. The optimal cooling schedule is (asymptotically) of the form η(t)=/lnt, with η(t) the learning parameter at time t and a constant, dependent on the reference learning parameters for the various transitions. In some simple cases, can be calculated. Simulations confirm the theoretical results.
- Received 2 November 1992
DOI:https://doi.org/10.1103/PhysRevE.47.4457
©1993 American Physical Society