Culling and Teaching in Neuro-Evolution

By P. McQuesten, Risto Miikkulainen. 1997

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, background): “McQuesten and Miikkulainen (1997) showed that neuroevolution can beneﬁt from parent networks teaching their offspring through backpropagation.”
Evolutionary Computation for Reinforcement Learning (2012, background): “ents (McQuesten and Miikkulainen, 1997), trained them to predict state transitions (Nolfi et al, 1994), and trained them to teach themselves (Nolfi and Parisi, 1997).”
Evolutionary Function Approximation for Reinforcement Learning (2006, background): “Stanley and Miikkulainen (Stanley and Miikkulainen, 2002) present a full description.”
Evolving plastic neural networks with novelty search (2010, background): “Furthermore, McQuesten and Miikkulainen (1997) showed that NE can benefit from parent networks teaching their offspring through backpropagation.”
Evolving adaptive neural networks with and without adaptive synapses (2003, background): “McQuesten and Miikkulainen (1997) showed that parent networks can teach their offspring using backpropagation.”
Modeling systems with internal state using evolino (2005, background): “Although Evolino does not use learning in the traditional gradient-descent sense, it is related to other hybrid evolutionary methods that adapt weight values during interaction with the evaluation environment [16, 25, 14].”