Sciweavers

Share
CEC
2008
IEEE

Learning what to ignore: Memetic climbing in topology and weight space

8 years 9 months ago
Learning what to ignore: Memetic climbing in topology and weight space
— We present the memetic climber, a simple search algorithm that learns topology and weights of neural networks on different time scales. When applied to the problem of learning control for a simulated racing task with carefully selected inputs to the neural network, the memetic climber outperforms a standard hill-climber. When inputs to the network are less carefully selected, the difference is drastic. We also present two variations of the memetic climber and discuss the generalization of the underlying principle to population-based neuroevolution algorithms.
Julian Togelius, Faustino J. Gomez, Jürgen Sc
Added 29 May 2010
Updated 29 May 2010
Type Conference
Year 2008
Where CEC
Authors Julian Togelius, Faustino J. Gomez, Jürgen Schmidhuber
Comments (0)
books