The Dynamics of Associative Learning in Evolved Model Circuits

Authors:
Phattanard Phattanasri;Hillel J. Chiel;Randall D. Beer
Affiliations:
Department of Electrical Engineering and Computer Science,Case Western Reserve University, Cleveland, OH 44106;Departments of Biology, Neurosciences, and BiomedicalEngineering Case Western Reserve University Cleveland, OH 44106;Cognitive Science Program, Department of Computer Science,Department of Informatics, Indiana University, Bloomington, IN 47406
Venue:
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Year:
2007

Citing 14
Cited 3

Exploring adaptive agency II: simulating the evolution of associative learning

Proceedings of the first international conference on simulation of adaptive behavior on From animals to animats
Learning rules from neurobiology

The neurobiology of neural networks
Voyages through weight space: network models of an escape reflex in the leech

Proceedings of the workshop on "Locomotion Control in Legged Invertebrates" on Biological neural networks in invertebrate neuroethology and robotics
Original Contribution: Approximation of dynamical systems by continuous time recurrent neural networks

Neural Networks
Evolving dynamical neural networks for adaptive behavior

Adaptive Behavior
Sequential behavior and learning in evolved dynamical neural networks

Adaptive Behavior
Integrating reactive, sequential, and learning behavior using dynamical neural networks

SAB94 Proceedings of the third international conference on Simulation of adaptive behavior : from animals to animats 3: from animals to animats 3
Learning dynamical systems by recurrent neural networks from orbits

Neural Networks
Evolution of Plastic Control Networks

Autonomous Robots
Exploring Adaptive Agency III: Simulating the Evolution of Habituation and Sensitization

PPSN I Proceedings of the 1st Workshop on Parallel Problem Solving from Nature
Associative learning in evolved dynamical neural networks

Associative learning in evolved dynamical neural networks
The dynamics of discrete-time computation, with application to recurrent neural networks and finite state machine extraction

Neural Computation
Exploring the T-Maze: evolving learning-like robot behaviors using CTRNNs

EvoWorkshops'03 Proceedings of the 2003 international conference on Applications of evolutionary computing
Fixed-weight on-line learning

IEEE Transactions on Neural Networks

Associative Learning on a Continuum in Evolved Dynamical Neural Networks

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Adapting to your body

ECAL'07 Proceedings of the 9th European conference on Advances in artificial life
The dynamics of associative learning in an evolved situated agent

ECAL'07 Proceedings of the 9th European conference on Advances in artificial life

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this article, we evolve and analyze continuous-time recurrent neural networks capable of associating the smells of different foods with edibility or inedibility in different environments. First, we present an in-depth analysis of this task, highlighting the evolutionary challenges it poses and how these challenges informed our experimental design. Next, we describe the evolution of nonplastic neural circuits that can solve this food edibility learning problem. We then show that the dynamics of the best evolved nonplastic circuits instantiate finite state machines that capture the combinatorial structure of this task. Finally, we demonstrate that successful circuits with Hebbian synaptic plasticity can also be evolved, but that such circuits do not utilize their synaptic plasticity in a traditional way.