Production systems, neural networks, and hybrid models

Production systems, neural networks, and hybrid models 

Relatively few attempts have been made to model schema acquisition and use. To be sure, the interpretation of a number of models depends upon the concept of a schema, but the structure of the schema itself is not part of the model. Consequently, to look at existing models of schemas we must broaden our view so that it encompasses not only explicit schema models but also models that are similar to those presented in the next few chapters but that are not focused on schemas. These latter models are models of learning, performance, and recognition. They tend to be either production system models or connectionist models. 

The issue of form, which is manifested in the symbolic versus connectionist arguments, is nevertheless only one aspect of cognitive modeling. At least two others also deserve attention. One concerns functionality What is the model to do The second has to do 

The shift in focus that accompanied the advent of production system models was enormous. It was no longer sufficient to consider only whether an individual learned or did not learn one also had to consider the nature of what was learned. Production system models were much more detailed than mathematical models. They 

In Newell s early work (1973), as well as in his later development of SOAR (1992), he made it explicit that he considered the production system to be a theory of cognitive architecture. Thus, the way that knowledge was stored in human memory is an important part of his system and his theory. The basic storage mechanism, of course, is the production rule. In general, a production system comprises a set of rules, each having the form  

---

Chapter 12 describes three types of models production systems, neural networks, and hybrid models. The general structure of each is described as well as the most well known examples. 

Chapter 12. Production systems, neural networks, and hybrid models... 

---