Simulating Stages of Human Cognitive Development with Connectionist Models
Abstract
The psychological literature on stages of cognitive development was reviewed and found to contain support for the idea that stages represent ordinal, qualitative changes in organized knowledge structures. There was a lack of empirical support for the notions that stage transitions are abrupt and concurrent. All of these findings were found to be consistent with new connectionist models of cognitive development. A fundamental insight emerged from working with such models, namely, that stages result when a network solves part of a problem before solving all of the problem. Partial problem solving in connectionist networks is likely to occur under the following conditions: hidden unit herding, over-generalization, training pattern bias, and hidden unit recruitment.
Cite
Text
Shultz. "Simulating Stages of Human Cognitive Development with Connectionist Models." International Conference on Machine Learning, 1991. doi:10.1016/B978-1-55860-200-7.50025-8Markdown
[Shultz. "Simulating Stages of Human Cognitive Development with Connectionist Models." International Conference on Machine Learning, 1991.](https://mlanthology.org/icml/1991/shultz1991icml-simulating/) doi:10.1016/B978-1-55860-200-7.50025-8BibTeX
@inproceedings{shultz1991icml-simulating,
title = {{Simulating Stages of Human Cognitive Development with Connectionist Models}},
author = {Shultz, Thomas R.},
booktitle = {International Conference on Machine Learning},
year = {1991},
pages = {105-109},
doi = {10.1016/B978-1-55860-200-7.50025-8},
url = {https://mlanthology.org/icml/1991/shultz1991icml-simulating/}
}