Active Learning in Recurrent Neural Networks Facilitated by a Hebb-like Learning Rule with Memory

We demonstrate in this article that a Hebb-like learning rule with memory paves the way for active learning in the context of recurrent neural networks. We compare active with passive learning and a Hebb-like learning rule with and without memory for the problem of timing to be learned by the neural network. Moreover, we study the influence of the topology of the recurrent neural network. Our results from numerical simulations reveal that active learning decreases the learning time significantly only for the Hebb-like learning rule with memory whereas the learning rule without memory remains unaffected. This result can be observed in all investigated network topologies, indicating the robustness of this effect.