Globally convergent algorithms with local learning rates |
| |
Authors: | Magoulas G.D. Plagianakos V.P. Vrahatis M.N. |
| |
Affiliation: | Dept. of Inf. Syst. and Comput., Brunel Univ., London. |
| |
Abstract: | A novel generalized theoretical result is presented that underpins the development of globally convergent first-order batch training algorithms which employ local learning rates. This result allows us to equip algorithms of this class with a strategy for adapting the overall direction of search to a descent one. In this way, a decrease of the batch-error measure at each training iteration is ensured, and convergence of the sequence of weight iterates to a local minimizer of the batch error function is obtained from remote initial weights. The effectiveness of the theoretical result is illustrated in three application examples by comparing two well-known training algorithms with local learning rates to their globally convergent modifications. |
| |
Keywords: | |
|
|