Modeling Category Learning with Stochastic Optimization Methods

Many neural network (NN) models of categorization (e.g., ALCOVE) use a gradient algorithm for learning. These methods have been successful in reproducing group learning curves, but tend to underpredict variability in individuallevel data, particularly for attention allocation measures (Matsuka, 2002). In addition, many recent models of categorization have been criticized for not being able to replicate rapid changes in categorization accuracies and attention processes observed in the empirical studies (Macho 1997; Rehder & Hoffman, 2003). In this paper we introduce stochastic learning algorithms for NN models of human category learning and show that use of the algorithms can result in (a) rapid changes in accuracies and attention allocation, and (b) different learning trajectories and more realistic variability in individual-level.