Loughborough University Institutional Repository (Loughborough University) · 2008 · 121 citations · 12 references
Open access
Life SciencesAutonomous SystemsEvolutionary BiologyMemoryNeuroplasticitySynaptic PlasticityEvolutionary RoboticsLearning In Neural SystemsLearning-related PlasticityNeural PlasticityNeuromodulationReinforcement LearningEvolutionary Neural ControllersLearning-induced PlasticityNeural Plasticity EvolutionNeuromodulation Of PlasticityNeuromodulatory Control Of PlasticityNeuromodulatory Plasticity
Neuromodulation is considered a key factor for learning and memory in biological neural networks. Similarly, artificial neural networks could benefit from modulatory dynamics when facing certain types of learning problem. Here we test this hypothesis by introducing modulatory neurons to enhance or dampen neural plasticity at target neural nodes. Simulated evolution is employed to design neural control networks for T-maze learning problems, using both stan-dard and modulatory neurons. The results show that exper-iments where modulatory neurons are enabled achieve better learning in comparison to those where modulatory neurons are disabled. We conclude that modulatory neurons evolve autonomously in the proposed learning tasks, allowing for increased learning and memory capabilities.
12
Operant Reward Learning in <i>Aplysia</i> : Neuronal Correlates and Mechanisms
Björn Brembs, Fred D. Lorenzetti, Fredy D. Reyes et al. · Science · 2002 · 339 citations · Full text
Classical conditioning in a simple withdrawal reflex in Aplysia californica
TJ Carew, ER Kandel · Journal of Neuroscience · 1981 · 286 citations · Full text
Life Sciences, Neuroscience, Zoology +15