The 'moving targets' algorithm for training recurrent networks is reviewed and applied to a task which demonstrates the ability of this algorithm to use distant contextual information. Some practical difficulties are discussed, especially with regard to the minimization process. Results on performance and computational requirements of several different 2nd-order minimization algorithms are presented for moving target problems.
|Published - 1990
|Neural Networks for Statistical and Economic Data - Dublin, Republic of Ireland
Duration: 10 Dec 1990 → 11 Dec 1990
|Neural Networks for Statistical and Economic Data
|Dublin, Republic of Ireland
|10/12/90 → 11/12/90
- moving target