Safe mutations for deep and recurrent neural networks through output gradients
Authors:
Open Access
- 2 July 2018
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 117-124
Abstract
No abstract availableKeywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Evolving deep unsupervised convolutional networks for vision-based reinforcement learning2014
- Evolvability Is Inevitable: Increasing Evolvability without the Pressure to AdaptPLOS ONE, 2013
- Abandoning Objectives: Evolution Through the Search for Novelty AloneEvolutionary Computation, 2011
- A Hypercube-Based Encoding for Evolving Large-Scale Neural NetworksArtificial Life, 2009
- A Taxonomy for Artificial EmbryogenyArtificial Life, 2003
- Reducing the Time Complexity of the Derandomized Evolution Strategy with Covariance Matrix Adaptation (CMA-ES)Evolutionary Computation, 2003
- Evolving Neural Networks through Augmenting TopologiesEvolutionary Computation, 2002
- Evolution of digital organisms at high mutation rates leads to survival of the flattestNature, 2001
- Evolving artificial neural networksProceedings of the IEEE, 1999
- Long Short-Term MemoryNeural Computation, 1997