Thu, 21 Aug 2008 15:30:02 BST CiteULike: kapfelba backprop http://www.citeulike.org/user/kapfelba/tag/backprop CiteULike.org en-gb Copyright © 2004-2008 citeulike.org http://www.citeulike.org/user/kapfelba/article/790395 <i>Neural Comput, Vol. 13, No. 6. (June 2001), pp. 1199-1241.</i><br /><br />Computational models in cognitive neuroscience should ideally use biological properties and powerful computational principles to produce behavior consistent with psychological findings. Error-driven backpropagation is computationally powerful and has proven useful for modeling a range of psychological data but is not biologically plausible. Several approaches to implementing backpropagation in a biologically plausible fashion converge on the idea of using bidirectional activation propagation in interactive networks to convey error signals. This article demonstrates two main points about these error-driven interactive networks: (1) they generalize poorly due to attractor dynamics that interfere with the network's ability to produce novel combinatorial representations systematically in response to novel inputs, and (2) this generalization problem can be remedied by adding two widely used mechanistic principles, inhibitory competition and Hebbian learning, that can be independently motivated for a variety of biological, psychological, and computational reasons. Simulations using the Leabra algorithm, which combines the generalized recirculation (GeneRec), biologically plausible, error-driven learning algorithm with inhibitory competition and Hebbian learning, show that these mechanisms can result in good generalization in interactive networks. These results support the general conclusion that cognitive neuroscience models that incorporate the core mechanistic principles of interactivity, inhibitory competition, and error-driven and Hebbian learning satisfy a wider range of biological, psychological, and computational constraints than models employing a subset of these principles. Generalization in interactive networks: the benefits of inhibitory competition and Hebbian learning. RC O'Reilly Neural Comput, Vol. 13, No. 6. (June 2001), pp. 1199-1241. 2006-08-09T05:30:37-00:00 2001 Neural Comput 0899-7667 13 6 1199 1241 backprop biology connectionism hebbian models pdp semisupervised_learning http://www.citeulike.org/user/kapfelba/article/2658822 <i>Neural Comput., Vol. 8, No. 5. (July 1996), pp. 895-938.</i> Biologically plausible error-driven learning using local activation differences: the generalized recirculation algorithm Randall O'Reilly Neural Comput., Vol. 8, No. 5. (July 1996), pp. 895-938. 2008-04-11T20:34:13-00:00 1996 Neural Comput. 0899-7667 8 5 895 938 MIT Press backprop biology brain_organization connectionism generec models pdp semisupervised_learning