Learning and Evolution in Neural Networks

By Stefano Nolfi, Domenico Parisi, Jeffrey L. Elman. 1994

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

Deep learning in neural networks: An overview (2014, background): “represented by a population of NNs improved through mutations and/or repeated recombinations of the population’s fittest individuals (e.g., Montana and Davis, 1989; Fogel et al., 1990; Maniezzo, 1994; Happel and Murre, 1994; Nolfi et al., 1994b).”
Combinations of genetic algorithms and neural networks: a survey of the state of the art (1992, methodology): “Brill, Brown, and Martin (1992) also used a genetic algorithm to select the feature set for a KNN classifier.”
The evolution of a generalized neural learning rule (2016, methodology): “These inputs are the same as those used in [4].”
Structure-Adaptable Digital Neural Networks (1999, methodology): “1 Evolutionary design of arti cial neural networks Evolutionary techniques such as genetic algorithms have also been proposed for the design of arti cial neural networks [21, 148, 240].”
Evolving Artiicial Neural Networks (2007, background): “Various models have been proposed [257, 258, 259, 260, 261, 262, 263, 264, 265, 266, 267, 268, 269, 270, 271] but most of them deal with the issue of how learning can guide evolution [257, 258, 259, 260] and the relationship between the evolution of architectures and that of connection weights [261,”
Exploring the effects of Lamarckian and Baldwinian learning in evolving recurrent neural networks (1997, methodology): “In this paper, we explore the e ects of two approaches of embedding learning into GAs, namely the Lamarckian and the Baldwinian1 learning mechanisms [1], [3], [4], [7].”
Evolution of homing navigation in a real mobile robot (1996, background): “Some experimental results on the evolution of simulated learning agents have shown both a speed-up in the convergence time [38] and the ability to deal with a very complex environment [39].”
Computational Genetics, Physiology, Metabolism, Neural Systems, Learning, Vision, and Behavior or PolyWorld: Life in a New Context (1997, background): “Nolfi et al [34] and Parisi et al [36] have explored evolving the connection strengths in small, fixed-architecture feed-forward neural networks controlling simple movement strategies in organisms evolved to seek food.”
Learning in spiking neural networks (2013, background): “In addition to these, there is one further form of adaptation of neural networks which spans a time period which is longer than the life of an individual: evolution (Nolfi et al., 1994).”
Neural Modularity Helps Organisms Evolve to Learn New Skills without Forgetting Old Skills (2015, background): “Compared to behaviors defined solely by evolution, evolving agents that learn leads to better solutions in fewer generations [48, 50, 51], improved adaptability to changing environments [48, 49], and enables evolving solutions for larger neural networks [48].”
Evolutionary Function Approximation for Reinforcement Learning (2006, methodology): “This biologically intuitive combination has been applied to computational systems in the past [1, 5, 8, 10, 12, 18] but never, to my knowledge, to aid the”
Evolving artificial neural networks (1999, background): “Various models have been proposed [257]–[271], but most of them deal with the issue of how learning can guide evolution [257]–[260] and the relationship between the evolution of architectures and that of connection weights [261]–[263].”
Evolution and Learning in an Intrinsically Motivated Reinforcement Learning Robot (2007, background): “One of the most important distinctions between the two adaptive mechanisms is the time scale within which they operate [1].”
On the design of neural networks in the brain by genetic evolution. (2000, methodology): “Some of the applications that are potentially relevant to understanding biological nervous systems range from computer simulated animats ( Nolfi et al., 1994; Gracias et al., 1996; Huber et al., 1996; Lund and Parisi, 1996) to behavioural robotics (Floreano and Mondada, 1994; Hoshino and Tsuchida, ”