A Simple Recurrent Network for Implicit Learning of Temporal Sequences
- 133 Downloads
A behavioural paradigm for learning arbitrary visuo-motor associations established that human observers learn to associate visual objects with their corresponding motor responses faster if the objects follow a temporal rule rather than if they were presented in a random order. Here, we use a simple recurrent network with a back propagation training algorithm adapted to a reinforcement learning scheme. Our simulations fit quantitatively as well as qualitatively to the behavioural results, endorsing the role of temporal context in associative learning scenarios.
KeywordsElman network Sequence learning Reinforcement learning Visuo-motor associations Behavioural models
The authors acknowledge the support provided by the federal state Sachsen-Anhalt with the Graduiertenförderung (LGFG scholarship).
- 1.Ackley DH, Littman ML. Generalization and scaling in reinforcement learning. In: Advances in neural information processing systems 2. Morgan Kaufmann; 1990. p. 550–7.Google Scholar
- 2.Cleeremans A. Mechanisms of implicit learning: connectionist models of sequence processing. Cambridge:MIT;1993.Google Scholar
- 11.Sutton RS, Barto AG. Reinforcement learning: an introduction. Adapt Comput Mach Learn. 1998;Mit Pr.Google Scholar