A Neural Network-Based Approach to Modeling the Allocation of Behaviors in Concurrent Schedule, Variable Interval Learning

In this paper we present a neural network-based model of the acquisition of choice behaviors. We employ a multi-layer perceptron, trained using backpropagation with a modified desired-output vector, to model behavior in concurrent-schedule, variable-interval, reinforcing learning situations. We show that our model can be used to describe and predict steady state behavior and learning patterns at the molar level.