Model Selection in Committees of Evolved Convolutional Neural Networks Using Genetic Algorithms
作者： Alejandro Baldominos , Yago Saez , Pedro Isasi
DOI: 10.1007/978-3-030-03493-1_39
关键词: Neuroevolution 、 Hyperparameter 、 Model selection 、 Convolutional neural network 、 Artificial intelligence 、 Computer science 、 Artificial neural network 、 Evolutionary algorithm
摘要: Neuroevolution is a technique that has been successfully applied for over three decades in order to optimize certain aspects of neural networks by applying evolutionary algorithms. However, only the recent years, increase computational resources enabled apply such techniques deep and convolutional networks, where number hyperparameters significantly large.
springer.com
sci-hub.st 参考文章(23)
Yohannes Kassahun, Gerald Sommer, Efficient reinforcement learning through Evolutionary Acquisition of Neural Topologies. the european symposium on artificial neural networks. pp. 259- 266 ,(2005)
Phillip Verbancsics, Josh Harguess, Image Classification Using Generative Neuro Evolution for Deep Learning workshop on applications of computer vision. pp. 488- 493 ,(2015) , 10.1109/WACV.2015.71
Dan Claudiu Ciresan, Ueli Meier, Luca Maria Gambardella, Jurgen Schmidhuber, Convolutional Neural Network Committees for Handwritten Character Classification international conference on document analysis and recognition. pp. 1135- 1139 ,(2011) , 10.1109/ICDAR.2011.229
Pierre Geurts, Damien Ernst, Louis Wehenkel, Extremely randomized trees Machine Learning. ,vol. 63, pp. 3- 42 ,(2006) , 10.1007/S10994-006-6226-1
Kenneth O. Stanley, Risto Miikkulainen, Evolving neural networks through augmenting topologies Evolutionary Computation. ,vol. 10, pp. 99- 127 ,(2002) , 10.1162/106365602320169811
X. Yao, Y. Liu, A new evolutionary system for evolving artificial neural networks IEEE Transactions on Neural Networks. ,vol. 8, pp. 694- 713 ,(1997) , 10.1109/72.572107
Jan Koutník, Juergen Schmidhuber, Faustino Gomez, Evolving deep unsupervised convolutional networks for vision-based reinforcement learning genetic and evolutionary computation conference. pp. 541- 548 ,(2014) , 10.1145/2576768.2598358
Steven R Young, Derek C Rose, Thomas P Karnowski, Seung-Hwan Lim, Robert M Patton, None, Optimizing deep learning hyper-parameters through an evolutionary algorithm ieee international conference on high performance computing data and analytics. pp. 4- ,(2015) , 10.1145/2834892.2834896
Francisco Javier Ordóñez, Daniel Roggen, Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition Sensors. ,vol. 16, pp. 115- ,(2016) , 10.3390/S16010115
Frank Hutter, Ilya Loshchilov, CMA-ES for Hyperparameter Optimization of Deep Neural Networks arXiv: Neural and Evolutionary Computing. ,(2016)