Book contents
- Frontmatter
- Contents
- Preface
- Acknowledgments
- I Fundamentals
- II Schemas and instruction
- III Learning from instruction
- IV Schemas and assessment
- V Schema models
- 12 Production systems, neural networks, and hybrid models
- 13 The performance model
- 14 The learning model
- 15 The full schema model
- 16 Some concluding remarks on schema theory
- Notes
- References
- Name index
- Subject index
12 - Production systems, neural networks, and hybrid models
Published online by Cambridge University Press: 22 October 2009
- Frontmatter
- Contents
- Preface
- Acknowledgments
- I Fundamentals
- II Schemas and instruction
- III Learning from instruction
- IV Schemas and assessment
- V Schema models
- 12 Production systems, neural networks, and hybrid models
- 13 The performance model
- 14 The learning model
- 15 The full schema model
- 16 Some concluding remarks on schema theory
- Notes
- References
- Name index
- Subject index
Summary
Until quite recently, cognitive scientists have tended to adopt one of two competing views about how to model the various mechanisms of cognition. On the one hand is the production system approach, which builds on condition-action rules. John R. Anderson's (1983) ACT* and Allen Newell's (1992) SOAR are exemplars. Such models are sometimes referred to as symbolic systems. On the other hand is the neural network approach. Models of this type are also called connectionist models or parallel distributed processing models. The PDP models of McClelland, Rumelhart and the PDP Research Group (1986) fall into this category. Now, a third alternative has appeared, one that merges these two approaches. Models illustrating this new approach are called hybrid models of cognition. There are, as yet, few examples. Not surprisingly, the hybrid model approach appears to be the best alternative for modeling schemas.
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.
- Type
- Chapter
- Information
- Schemas in Problem Solving , pp. 317 - 339Publisher: Cambridge University PressPrint publication year: 1995