Forming Neural Networks Through Efficient and Adaptive Coevolution

By David E. Moriarty, 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.

Citations in the corpus

The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities (2018, neutral): “One of the entries, however, was a player based on the SANE neuroevolution approach for playing Othello [96, 98].”
Spectrum-Diverse Neuroevolution With Unified Neural Models (2017, background): “Many works investigated the evolution of fixed-topology neural networks [3]–[6].”
Genetic Representation and Evolvability of Modular Neural Controllers (2010, background): “However, when the effect of mutations was constrained by a hand-designed modular network structure separating the two subproblems, evolution was able to find optimal neural controllers consistently.”
Meta learning evolutionary arti ! cial neural networks (2004, background): “Several high level coding schemes like graph generation system [49], symbiotic adaptive neuro-evolution (SANE) [62,65], marker based genetic coding [36], L-systems [13], cellular encoding [38], fractal representation [58], etc.”
Meta learning evolutionary artificial neural networks (2004, background): “will define a set of neurons, their spatial arrangement and their efferent connectivity. Several high level coding schemes like graph generation system [49], Symbiotic Adaptive Neuro-Evolution (SANE) [62] [65], marker based genetic coding [36], L-systems [13], cellular encoding [38], fractal represe”
Evolving Neural Networks through Augmenting Topologies (2002, background): “Neuroevolution (NE), the artificial evolution of neural networks using genetic algorithms , has shown great promise in complex reinforcement learning tasks (Gomez and Miikkulainen, 1999; Gruau et al., 1996; Moriarty and Miikkulainen, 1997; Potter et al., 1995; Whitley et al., 1993).”
Cooperative Coevolution: An Architecture for Evolving Coadapted Subcomponents (2000, methodology): “For example, in the SANE system (Moriarty 1997; Moriarty and Miikkulainen 1997) each individual in the population represents a single neuron by specifying which input and output units it connects to and the weights on each of its connections.”
Evolutionary Computation for Reinforcement Learning (2012, background): “As Moriarty and Mikkulainen say, " neuron-level evolution takes advantage of the a priori knowledge that individual neurons constitute basic components of neural networks " (Moriarty and Miikkulainen, 1997).”
Evolutionary optimization in uncertain environments-a survey (2005, methodology): “To solve this problem, methods known as fitness assignment for estimating fitness values have been developed in cooperative coevolutionary systems [138], [157], [212].”
Metaheuristic design of feedforward neural networks: A review of two decades of research (2017, methodology): “A cooperative coevolution neural network process—inspired by virtual subpopulation approach [266]— was proposed in [268], which was a symbiotic, adaptive neuroevolution (SANE) algorithm for constructing FNN in a dynamic environment.”
Modelling brain emergent behaviours through coevolution of neural agents (2006, background): “Evidently, the coevolutionary process could be supported by the maintenance of successful collaborator assemblies, as in Moriarty and Miikkulainen (1997).”