A detailed description of a layered network model is provided, with computer simulations of key associative learning phenomena and predictions generated from the model. The model is compared to more conventional theories of learning to learn and configural learning. (SLD)

The Educational Technology Center (ETC) Complex Systems Project was initiated to explore ways of using computers to help students understand systems which have often proven too complex for most high school students to understand. Preliminary work concentrated on the cognitive processes involved in modeling simple systems. This paper describes an…

This paper describes further research on a learning procedure for layered networks of deterministic, neuron-like units, described by Rumelhart et al. The units, the way they are connected, the learning procedure, and the extension to iterative networks are presented. In one experiment, a network learns a set of filters, enabling it to discriminate…