Evolving adaptive neural networks with and without adaptive synapses

By Kenneth O. Stanley, Bobby D. Bryant, Risto Miikkulainen. 2003

129 citations recorded by the source corpus.

How researchers see this paper

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

In Artificial Intelligence

Citations in the corpus

Novelty of behaviour as a basis for the neuro-evolution of operant reward learning (2009, background): “Which approach leads to better evolution of adaptive behaviour is still debated [7, 15].”
Real-time Hebbian Learning from Autoencoder Features for Control Tasks (2014, background): “…artificial life and related fields (Baxter, 1992; Floreano and Urzelai, 2000; Niv et al., 2002; Soltoggio et al., 2008, 2007; Soltoggio and Jones, 2009; Soltoggio and Stanley, 2012; Risi and Stanley, 2010; Risi et al., 2011; Risi and Stanley, 2012; Stanley et al., 2003; Coleman and Blair, 2012).”
Evolving Plastic Neural Networks for Online Learning: Review and Future Directions (2012, methodology): “This requires producing environments that are different in some way for each generation and/or change in some way during a fitness evaluation [4, 20, 25, 27].”
Using a map-based encoding to evolve plastic neural networks (2011, background): “However, it has been shown that fixed [30] or recursive [31] networks can often perform better than adaptive networks in these tasks, thanks to the internal dynamics created by recurrent connections.”
Discovering Gated Recurrent Neural Network Architectures (2018, methodology): “For e.g. in reinforcement learning domain, evolutionary algorithms like NEAT are quite competitive with Q-learning and policy gradient methods ( Stanley et al. (2003)).”
Continual Learning through Evolvable Neural Turing Machines (2016, background): “In order to enable these evolving ANNs to learn during their lifetime, efforts have been made to allow them to adapt online and learn from past experience [10, 11, 12, 13, 14].”
Evolving Neural Turing Machines for Reward-based Learning (2016, background): “Adaptive neural networks can either change through local Hebbian learning rules [6], in which connection weights are modified based on neural activation [14, 4], or recurrent neural networks (RNNs) that store activation patterns through recurrent connections [1].”
Evolutionary Computation for Reinforcement Learning (2012, background): “To get around the problem of missing labels, researchers have employed unsupervised learning (Stanley et al, 2003), trained individuals to resemble their parents (McQuesten and Miikkulainen, 1997), trained them to predict state transitions (Nolfi et al, 1994), and trained them to teach themselves…”
How novelty search escapes the deceptive trap of learning to learn (2009, methodology): “NEAT has proven successful in diverse control and decisionmaking domains [1, 21, 22].”
Evolving plastic neural networks with novelty search (2010, methodology): “…was originally developed to evolve ANNs to solve difficult control and sequential decision tasks and has proven successful in a wide diversity of domains (Aaltonen et al., 2009; Stanley et al., 2003, 2005; Stanley & Miikkulainen, 2002; Taylor, Whiteson, & Stone, 2006; Whiteson & Stone, 2006).”
Adaptation of Robot Behaviour through Online Evolution and Neuromodulated Learning (2012, methodology): “In the dangerous foraging domain [31], each trial contained only a specific type of food, either nutritious or poisonous.”
Evolving Deep LSTM-based Memory Networks using an Information Maximization Objective (2016, background): “First step towards adaptive behavior is to memorize past events and utilize them for future decision making [23].”
Continual and One-Shot Learning Through Neural Networks with Dynamic External Memory (2017, background): “Adaptive neural networks can either change through local Hebbian learning rules [18], in which connection weights are modified based on neural activation [8, 9, 14], or recurrent neural networks (RNNs) that store activation patterns through recurrent connections [10].”