A study of the Lamarckian evolution of recurrent neural networks

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.