P. J. Werbos. Backpropogation through time: what it does and how to do it. Proceedings of IEEE, 78(10):1550-- 1560, 1990. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
A Cellular Genetic Algorithm for training Recurrent Neural.. - Ku, Mak, Siu (1995) (Correct)
....nodes, and it has a feedback loop connecting itself. Therefore, RNNs have the capability of dealing with spatiotemporal relationship, of which feed forward neural networks are lack. In order to determine the appropriate connection weights in RNNs, a number of training algorithms have been proposed [7, 8, 10]. These algorithms are gradient descent methods where the weights in the RNNs are adjusted continually in order to minimize an error function. Genetic Algorithms (GAs) are search algorithms based on the mechanics of natural selection and natural genetics [4] The underlying principle is the ....
P. J. Werbos. Backpropogation through time: what it does and how to do it. Proceedings of IEEE, 78(10):1550-- 1560, 1990.
Adding Learning to Cellular Genetic Algorithms for Training.. - Ku, Mak, Siu (1998) (1 citation) (Correct)
....them to preserve past states of the networks. Therefore, RNNs have the capability of dealing with spatio temporal problems which have been found to be difficult for feedforward networks [36] In order to determine the weights of RNNs, a number of training algorithms have been proposed [38] [44], 48] These algorithms are based on some gradient descent approaches where the weights in the RNNs are adjusted continually in order to minimize an error function. Genetic algorithms (GAs) 12] 16] 33] 34] in contrast, are stochastic search algorithms based on the mechanics of natural ....
P. J. Werbos. Backpropogation through time: what it does and how to do it. Proceedings of IEEE, 78(10):1550-- 1560, 1990.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC