Abstract
This chapter introduces a hierarchy of concepts to classify the goals and the methods used in articles that mix neuro-evolution and synaptic plasticity. We propose definitions of “behavioral robustness” and oppose it to “reward-based behavioral changes”; we then distinguish the switch between behaviors and the acquisition of new behaviors. Last, we formalize the concept of “synaptic General Learning Abilities” (sGLA) and that of “synaptic Transitive learning Abilities (sTLA)”. For each concept, we review the literature to identify the main experimental setups and the typical studies.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
We focus our discussion on classic neurons (as used in classic machine learning) and population-based models of neurons (e.g. leaky integrators) because they are the neuron models that are used by most of the community. Spiking neuron models can make use of other plasticity mechanisms (e.g. STDP) that will not be described here.
References
C.H. Bailey, M. Giustetto, Y.Y. Huang, R.D. Hawkins, E.R. Kandel, Is heterosynaptic modulation essential for stabilizing Hebbian plasticity and memory? Nature Rev. Neurosci. 1(1), 11–20 (2000)
J. Blynel, D. Floreano, Levels of dynamics and adaptive behavior in evolutionary neural controllers, in Conference on Simulation of Adaptive Behavior (SAB) (2002), pp. 272–281
D.J. Chalmers, The Evolution of Learning: An Experiment in Genetic Connectionism (Connectionist Models Summer School, 1990)
J. Clune, K.O. Stanley, R.T. Pennock, C. Ofria, On the performance of indirect encoding across the continuum of regularity. IEEE Trans. Evol. Comput. 15(3), 346–367 (2011)
N.D. Daw, Y. Niv, P. Dayan, Uncertainty-based competition between prefrontal and dorsolateral striatal systems for behavioral control. Nature Neurosci. 8(12), 11–1704 (2005)
D. Floreano, Evolution of plastic neurocontrollers for situated agents, in Conference on Simulation of Adaptive Behavior (SAB) (1996)
D. Floreano, P. Dürr, C. Mattiussi, Neuroevolution: from architectures to learning. Evol. Intell. 1(1), 47–62 (2008)
D. Floreano, C. Mattiussi, Bio-inspired Artificial Intelligence: Theories, Methods, and Technologies (The MIT Press, 2008)
S. Haykin, Neural networks: a comprehensive foundation (Prentice Hall, Upper Saddle River, 1999)
J. Kodjabachian, J.-A. Meyer, Evolution and development of neural controllers for locomotion, gradient-following, and obstacle-avoidance in artificial insects. IEEE Trans. Neural Networks 9(5), 796–812 (1998)
T. Kondo, Evolutionary design and behavior analysis of neuromodulatory neural networks for mobile robots control. Appl. Soft Comput. 7(1), 189–202 (2007)
J.-B. Mouret, S. Doncieux, Using behavioral exploration objectives to solve deceptive problems in neuro-evolution, in Conference on genetic and evolutionary computation (GECCO) (2009)
J.-B. Mouret, S. Doncieux, B. Girard, Importing the computational neuroscience toolbox into neuro-evolution—application to basal ganglia, in Conference on genetic and evolutionary computation (GECCO) (2010)
Y. Niv, D. Joel, I. Meilijson, E. Ruppin, Evolution of reinforcement learning in uncertain environments: a simple explanation for complex foraging behaviors. Adapt. Behav. 10(1), 5–24 (2002)
S. Nolfi, How learning and evolution interact: the case of a learning task which differs from the evolutionary task. Adapt. Behav. 4(1), 81–84 (1999)
S. Nolfi, O. Miglino, D. Parisi, Phenotypic plasticity in evolving neural networks. in From Perception to Action Conference (IEEE, 1994), pp. 146–157
S. Risi, K.O. Stanley, Indirectly encoding neural plasticity as a pattern of local rules, in Conference on Simulation of Adaptive Behavior (SAB) (2010)
S. Risi, S.D. Vanderbleek, C.E. Hughes, K.O. Stanley, How novelty search escapes the deceptive trap of learning to learn, in Conference on genetic and evolutionary computation (GECCO) (2009)
W. Schultz, P. Dayan, P.R. Montague, A neural substrate of prediction and reward. Science 275(5306), 1593–1599 (1997)
B.F. Skinner, Operant behavior. Am. Psychol. 18(8), 503 (1963)
A. Soltoggio, J.A. Bullinaria, C. Mattiussi, P. Dürr, D. Floreano, Evolutionary advantages of neuromodulated plasticity in dynamic, reward-based scenarios. Artif. Life 11, 569 (2008)
A. Soltoggio, P. Dürr, C. Mattiussi, D. Floreano, Evolving neuromodulatory topologies for reinforcement learning-like problems, in IEEE Congress on Evolutionary Computation (CEC) (2007)
A. Soltoggio, B. Jones, Novelty of behaviour as a basis for the neuro-evolution of operant reward learning, in Conference on genetic and evolutionary computation (GECCO) (2009)
K.O. Stanley, B.D. Bryant, R. Miikkulainen, Evolving adaptive neural networks with and without adaptive synapses, in IEEE Congress on Evolutionary Computation (CEC) (2003)
K.O. Stanley, D. D’Ambrosio, J. Gauci, A hypercube-based indirect encoding for evolving large-scale neural networks. Artif. Life 15(2), 185–212 (2009)
K.O. Stanley, R. Miikkulainen, Evolving neural networks through augmenting topologies. Evol. Comput. 10(2), 99–127 (2002)
R.S. Sutton, A.G. Barto, Reinforcement learning: An introduction (The MIT press, 1998)
P. Tonelli, J.-B. Mouret, On the relationships between synaptic plasticity and generative systems, in Conference on genetic and evolutionary computation (GECCO) (2011)
P. Tonelli, J.-B. Mouret, On the relationships between generative encodings, regularity, and learning abilities when evolving plastic artificial neural networks. PLoS One. 8(11), e79138 (2013)
J. Urzelai, D. Floreano, Evolution of adaptive synapses: robots with fast adaptive behavior in new environments. Evol. Comput. 9(4), 495–524 (2001)
Acknowledgments
This work was funded by the EvoNeuro project (ANR-09-EMER-005-01) and the Creadapt project (ANR-12-JS03-0009).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Mouret, JB., Tonelli, P. (2014). Artificial Evolution of Plastic Neural Networks: A Few Key Concepts. In: Kowaliw, T., Bredeche, N., Doursat, R. (eds) Growing Adaptive Machines. Studies in Computational Intelligence, vol 557. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-55337-0_9
Download citation
DOI: https://doi.org/10.1007/978-3-642-55337-0_9
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-55336-3
Online ISBN: 978-3-642-55337-0
eBook Packages: EngineeringEngineering (R0)