GenNets: genetically programmed neural nets-using the genetic algorithm to train neural nets whose inputs and/or outputs vary in time

@inproceedings{citeulike:3018439, abstract = {The author shows that the generic algorithm (GA) can be applied successfully to training nonconvergent networks, and presents some examples of their extraordinary behavioral versatility. He first gives a brief summary of the GA and the genetic programming of neural networks. He shows how GP techniques were used to evolve GenNets with specified operating conditions, and demonstrates some of the extraordinary capacities of time-dependent GenNets. He also makes a plea to the neural network research community to `shift its sights upwards' by devoting more effort to thinking about `dynamic' neural networks in general, and the theory of GenNet dynamics and `evolvability' in particular}, author = {de Garis, H. }, booktitle = {Neural Networks, 1991. 1991 IEEE International Joint Conference on}, citeulike-article-id = {3018439}, doi = {http://dx.doi.org/10.1109/IJCNN.1991.170594}, journal = {Neural Networks, 1991. 1991 IEEE International Joint Conference on}, keywords = {indirect}, pages = {1391--1396 vol.2}, posted-at = {2008-07-18 14:52:22}, priority = {2}, title = {GenNets: genetically programmed neural nets-using the genetic algorithm to train neural nets whose inputs and/or outputs vary in time}, url = {http://dx.doi.org/10.1109/IJCNN.1991.170594}, year = {1991} }

TY - CONF ID - citeulike:3018439 L3 - citeulike-article-id:3018439 TI - GenNets: genetically programmed neural nets-using the genetic algorithm to train neural nets whose inputs and/or outputs vary in time T2 - Neural Networks, 1991. 1991 IEEE International Joint Conference on JF - Neural Networks, 1991. 1991 IEEE International Joint Conference on SP - 1391 EP - 1396 vol.2 N2 - The author shows that the generic algorithm (GA) can be applied successfully to training nonconvergent networks, and presents some examples of their extraordinary behavioral versatility. He first gives a brief summary of the GA and the genetic programming of neural networks. He shows how GP techniques were used to evolve GenNets with specified operating conditions, and demonstrates some of the extraordinary capacities of time-dependent GenNets. He also makes a plea to the neural network research community to `shift its sights upwards' by devoting more effort to thinking about `dynamic' neural networks in general, and the theory of GenNet dynamics and `evolvability' in particular KW - indirect AU - de Garis, H PY - 1991/// UR - http://dx.doi.org/10.1109/IJCNN.1991.170594 ER -