Sirois, S., & Shultz, T. R. (1997). A neural network model of discrimination shifts. Proceedings of the Nineteenth Annual Conference of the Cognitive Science Society (p. 1053). Mahwah, NJ: Erlbaum.
It was recently claimed that feedforward neural networks cannot simulate what is considered to be rule-based behavior in adult humans (Raijmakers, van Koten, & Molenaar, 1996). Back-propagation networks learning discrimination shifts were found to behave in an associative way characteristic of young children. We suggest that these simulations are flawed by using layered networks on linear problems.
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.