Building Hybrid Connectionist Production Systems
Introduction:-Data communication between productions and neural networks take place through the working memory makes it possible to use the execution cycle of the production system as a control cycle for the whole hybrid connectionist production system.
The overall control is done with the use of production rules. Through production rules different modules can be chained in a sequence, one module using the output from another, the wholechain solving one task.
The inference is controlled through the production system's inference engine.
Loosely and tightly coupled hybrid connectionist production systems, in their structural varieties, can be realized in the above connectionist production system environment.
The solution procedure for each of the modules is defined either as a set of production rules, or as a neural network, to be trained with data.
The whole system is assembled in a way to be controlled by the inference engine of the production system, taking into account inference strategies, priorities and other requirements.
By mixing the symbolic production systems paradigm with the connectionist paradigm, each is enriched with the advantages of the other. A connectionist production system can perform:-
- Chain reasoning
- Approximate reasoning
- Fast computations
- Learning during execution
- Dealing both with data and rules as problem knowledge