Intellectual expertise means knowledge and ability that a person has that allows them to solve complex problems. It is important to understand how people become experts so that we can improve educational strategies, and help learners achieve their full academic potential. Unfortunately, the process of acquiring intellectual expertise is not well understood. Artificial neural networks (ANNs) have already been successful in modeling other types of human learning. This paper shows that they can also be trained as a model of expert human learning, and address many of the difficulties found in trying to study expertise in humans. The results confirm three hypotheses: (1) An artificial neural network can be used as a model to investigate how people learn under different training scenarios; (2) Different methods for delivering the training material result in different final performance; (3) The best performance is achieved by incrementally increasing the complexity of the material. These results provide educators with computational evidence that structured, integrated delivery methods are better for learners than oversimplification and isolation of learning tasks.

PDF, PS

In Proceedings of the 26th Annual Conference of the Cognitive Science Society 2004.

@inproceedings{kaczmarczyk:cogsci04, title={The Acquisition of Intellectual Expertise: A Computational Model}, author={Elizabeth C. Kaczmarczyk and Risto Miikkulainen}, booktitle={Proceedings of the 26th Annual Conference of the Cognitive Science Society}, url="http://www.cs.utexas.edu/users/ai-lab?kaczmarczyk:cogsci04", year={2004} }