Indirectly Encoding Neural Plasticity as a Pattern of Local Rules

By Sebastian Risi, Kenneth O. Stanley. 2010

102 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

AutoML-Zero: Evolving Machine Learning Algorithms From Scratch (2020, background): “Numerically or otherwise, some studies center on the method by which the optimizer is learned; it can vary widely from the use of gradient descent [2] to reinforcement learning [42] to evolutionary search with sophisticated developmental encodings [71].”
Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, methodology): “nection weights in EPANN may not be individually encoded in the genome, also plasticity may be coded in the genome to be expressed indirectly in the phenotype. Using a T-Maze domain as learning task, Risi and Stanley (2010) showed that HyperNEAT, which usually implements a compact encoding of weight”
A unified approach to evolving plasticity and neural geometry (2012, background): “Risi and Stanley [21] showed that this approach can solve a discrete T-Maze with every parameter for the entire evolved learning network compactly encoded by the CPPN. III.”
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): “Risi and Stanley [22] also developed a novel synaptic plasticity system able to evolve arbitrarily complex rules.”
On the Relationships between Generative Encodings, Regularity, and Learning Abilities when Evolving Plastic Artificial Neural Networks (2013, background): “Several papers report experiments in which neural networks with synaptic plasticity are evolved [2,15,18–24].”
Neuromodulation Improves the Evolution of Forward Models (2016, background): “Additionally, it has previously been shown that neuromodulation can enable organisms to adapt to changing environments [9, 21, 24, 25].”
Evolving Neuromodulatory Topologies for Plasticity in Video Game Playing (2016, background): “It has potential to be combined with other life-long learning methods such as hypothesis testing in distal reward learning [22], larger indirectly encoded networks [19], [16], overcoming deception in evolution of cognitive behaviors [12], and learning big collections of different behavior [3].”
Guided self-organization in indirectly encoded and evolving topographic maps (2014, background): “The main idea in adaptive HyperNEAT [16] is that CPPNs can not only encode connectivity patterns but also patterns of plasticity rules.”
Evolving Neural Turing Machines for Reward-based Learning (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 [14, 4, 1, 2, 10].”
The evolution of a generalized neural learning rule (2016, background): “A more advanced version, called adaptive EShyperNEAT, stores different Hebbian parameters for each connection using compositional pattern producing networks (CPPNs) [11].”
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].”