Please use this identifier to cite or link to this item:
|Title:||A study of the Lamarckian evolution of recurrent neural networks|
Recurrent neural networks
|Source:||IEEE transactions on evolutionary computation, Apr. 2000, v. 4, no. 1, p. 31-42 How to cite?|
|Journal:||IEEE transactions on evolutionary computation|
|Abstract:||Many frustrating experiences have been encountered when the training of neural networks by local search methods becomes stagnant at local optima. This calls for the development of more satisfactory search methods such as evolutionary search. However, training by evolutionary search can require a long computation time. In certain situations, using Lamarckian evolution, local search and evolutionary search can complement each other to yield a better training algorithm. This paper demonstrates the potential of this evolutionary-learning synergy by applying it to train recurrent neural networks in an attempt to resolve a long-term dependency problem and the inverted pendulum problem. This work also aims at investigating the interaction between local search and evolutionary search when they are combined. It is found that the combinations are particularly efficient when the local search is simple. In the case where no teacher signal is available for the local search to learn the desired task directly, the paper proposes introducing a related local task for the local search to learn, and finds that this approach is able to reduce the training time considerably.|
|Rights:||© 2000 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.|
This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
|Appears in Collections:||Journal/Magazine Article|
Show full item record
Citations as of Jan 14, 2017
WEB OF SCIENCETM
Citations as of Jan 15, 2017
Checked on Jan 15, 2017
Checked on Jan 15, 2017
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.