A unified approach to evolving plasticity and neural geometry

By Sebastian Risi, Kenneth O. Stanley. 2012

56 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering

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

In Electrical and Electronic Engineering

Citations in the corpus

Deep learning in neural networks: An overview (2014, neutral): “…(Kitano, 1990), Cellular Encoding (Gruau, Whitley, & Pyeatt, 1996), HyperNEAT (Clune, Stanley, Pennock, & Ofria, 2011; D’Ambrosio & Stanley, 2007; Stanley, D’Ambrosio, & Gauci, 2009; van den Berg & Whiteson, 2013) (extending NEAT; Section 6.6), and extensions thereof (e.g., Risi & Stanley, 2012).”
Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, methodology): “In contrast, certain types of EPANNs that evolve architectures with arbitrary depth, e.g. (Risi and Stanley, 2012), are effectively deep EPANNs.”
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).”
Overcoming deception in evolution of cognitive behaviors (2014, methodology): “Such approaches include applying incremental evolution [21], refined fitness functions [18], more complicated neural models [28] or additional helper objectives [12, 13].”
Evolving Plastic Neural Networks for Online Learning: Review and Future Directions (2012, methodology): “In most reinforcement learning experiments the fitness of an agent has been the amount of reward it received during its lifetime [20,25,27] or is at least strongly correlated with the reward received [15, 23].”
Evolving Neural Turing Machines for Reward-based Learning (2016, background): “While the continuous single T-Maze is challenging, it has been previously solved with adaptive neural networks [13, 11].”
Guided self-organization in indirectly encoded and evolving topographic maps (2014, methodology): “In the future it might be possible to combine a SOM-generating seed with a recent HyperNEAT extension called adaptive evolvablesubstrate HyperNEAT [17, 18].”
Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity (2018, methodology): “Evolved networks with neuromodulated plasticity were shown to outperform both non-neuromodulated and non-plastic networks in various tasks (e.g. Soltoggio et al. 2008; Risi & Stanley 2012; see Soltoggio et al. 2017 for a review).”
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].”