Incorporating an adaptive learning rate in a neural model of action selection

Cognitive Computational Neuroscience, 2018

Sverrir Thorgeirsson, Brent Komer, Chris Eliasmith


In previous work, we have implemented spiking neuron models that use a biologically realistic action selection system to solve complex cognitive tasks, including the Tower of Hanoi and semantic memory search. However, such models often require the fine-tuning of multiple parameters so that the model can reach a desired level of performance. Recently, we demonstrated that a local, online learning rule, which only requires a single parameter, the learning rate, is sufficient for teaching our model how to solve a general cognitive sequencing task. Here, we refine our method by showing that adding adaptive learning is more robust regarding our choice of parameters, and will achieve better performance on all versions of the cognitive task that we tested. These results provide a foundation for building complex cognitive models that require no hand-tuning of parameters.

Full text links


 External link

Supplementary information


Conference Proceedings

Cognitive Computational Neuroscience
Philadelphia, USA


Plain text