Training of artificial neural networks using safe mutations based on output gradients
作者： Joel Anthony Lehman , Kenneth Owen Stanley , Jeffrey Michael Clune
DOI:
关键词:
摘要: Abstract Systems and methods are disclosed herein for ensuring a safe mutation of a neural network. A processor determines a threshold value representing a limit on an amount of …
lens.org 参考文章(37)
Sriraman Kandhadai Raghunathan, Abhijeet Jaswal, Methods and systems for providing personalized and context-aware suggestions ,(2013)
J. Douglas Birdwell, Catherine Schuman, Mark E. Dean, Method and apparatus for constructing, using and reusing components and structures of an artifical neural network ,(2014)
Mengjiao Wang, Yu Cheng, Wen-Syan Li, System and method of fuel filling to minimize fuel cost ,(2013)
Luciana Salete Buriol, Marcus Ritt, Roger S. Reis, Mauricio Guilherme de Carvalho Resende, Methods and apparatus to determine network link weights ,(2010)
Diederik P. Kingma, Jimmy Ba, Adam: A Method for Stochastic Optimization arXiv: Learning. ,(2014)
John F Kolen, Stefan C Kremer, Gradient Flow in Recurrent Nets: the Difficulty of Learning Long-Term Dependencies ,(2001)
Yoshua Bengio, Xavier Glorot, Understanding the difficulty of training deep feedforward neural networks international conference on artificial intelligence and statistics. pp. 249- 256 ,(2010)
Christopher John Burges, John Stewart Denker, System and method for automated interpretation of input expressions using novel a posteriori probability measures and optimally trained information processing networks ,(1995)
Michael Seskin, Anthony J. Grichnik, Method and system for intelligent maintenance ,(2006)
Yoshua Bengio, Tomas Mikolov, Razvan Pascanu, On the difficulty of training recurrent neural networks international conference on machine learning. pp. 1310- 1318 ,(2013)