Generational versus steady-state evolution for optimizing neural network learning Export

@inproceedings{citeulike:2097535, abstract = {The use of simulated evolution is now a commonplace technique for optimizing the learning abilities of neural network systems. Neural network details such as architecture, initial weight distributions, gradient descent learning rates, and regularization parameters, have all been successfully evolved to result in improved performance. The author investigates which evolutionary approaches work best in this field. In particular, he compares the traditional generational approach to a more biologically realistic steady-state approach.}, author = {Bullinaria, J. A.}, booktitle = {Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on}, citeulike-article-id = {2097535}, citeulike-linkout-0 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1380984}, journal = {Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on}, keywords = {generational\_evolution, steady\_state}, pages = {2297--2302 vol.3}, posted-at = {2007-12-12 09:31:23}, priority = {2}, title = {Generational versus steady-state evolution for optimizing neural network learning}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1380984}, volume = {3}, year = {2004} }

TY - CONF ID - citeulike:2097535 L3 - citeulike-article-id:2097535 N2 - The use of simulated evolution is now a commonplace technique for optimizing the learning abilities of neural network systems. Neural network details such as architecture, initial weight distributions, gradient descent learning rates, and regularization parameters, have all been successfully evolved to result in improved performance. The author investigates which evolutionary approaches work best in this field. In particular, he compares the traditional generational approach to a more biologically realistic steady-state approach. JF - Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on EP - 2302 vol.3 TI - Generational versus steady-state evolution for optimizing neural network learning VL - 3 T2 - Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on SP - 2297 KW - generational_evolution KW - steady_state AU - Bullinaria, JA PY - 2004/// UR - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1380984 ER -