Shultz, T. R. (2006). Constructive
learning in the modeling of psychological development. In Y. Munakata & M. H. Johnson (Eds.), Processes of change in brain and cognitive development: Attention and
performance XXI (pp. 61-86).
Although many computational models of psychological development involve only learning, this paper examines the advantages of allowing artificial neural networks to grow as well as learn in such simulations. Comparisons of static and constructive network simulations of the same developmental phenomena bring this issue into clear focus. Constructive algorithms are found to be better at learning and at covering developmental stages and stage sequences. The relatively new sibling-descendant cascade-correlation algorithm (SDCC) decides whether to install each newly recruited hidden unit on the current highest layer or on a new layer. SDCC is applied to the problem of conservation acquisition in children. Results show no differences in comparison to previous conservation simulations done with standard cascade-correlation except for fewer network layers and connections with SDCC.
Abstracts, papers, chapters, and other documents are posted on this site as an efficient way to distribute reprints. The respective authors and publishers of these works retain all of the copyrights to this material. Anyone copying, downloading, bookmarking, or printing any of these materials agrees to comply with all of the copyright terms. Other than having an electronic or printed copy for fair personal use, none of these works may be reposted, reprinted, or redistributed without the explicit permission of the relevant copyright holders.
To obtain a PDF reprint of this particular article, signal your agreement with these copyright terms by clicking on the statement below.