Evolved Sensitive Periods in Learning
Kai Olav Ellefsen · 2013
In this paper we study age-varying plasticities across different components in an artificial neural network performing a rein-forcement learning task. An evolutionary algorithm is given the task of mapping the age of agents to the plasticity levels of different network components. The results show that patterns of plasticity resembling biological sensitive periods appear, and that these periods schedule learning across the compo-nents of the network, which leads to a reduction in the total learning effort while retaining the quality of learning. The sequencing of sensitive periods forms a cascade of partially-overlapping learning periods, which has been proposed as a way of organizing sensory development of abilities that de-pend on several interrelated brain functions.