Toward the evolution of symbols
Proceedings of the Second International Conference on Genetic Algorithms on Genetic algorithms and their application
Seeing the light: artificial evolution, real vision
SAB94 Proceedings of the third international conference on Simulation of adaptive behavior : from animals to animats 3: from animals to animats 3
Digital integrated circuits: a design perspective
Digital integrated circuits: a design perspective
Networks of spiking neurons: the third generation of neural network models
Transactions of the Society for Computer Simulation International - Special issue: simulation methodology in transportation systems
Dynamic stochastic synapses as computational units
Neural Computation
Evolutionary Robotics: The Biology,Intelligence,and Technology
Evolutionary Robotics: The Biology,Intelligence,and Technology
Spiking Neuron Models: An Introduction
Spiking Neuron Models: An Introduction
Evolving neural networks through augmenting topologies
Evolutionary Computation
Evolution of Adaptive Synapses: Robots with Fast Adaptive Behavior in New Environments
Evolutionary Computation
Evolvability of Neuromodulated Learning for Robots
LAB-RS '08 Proceedings of the 2008 ECSIS Symposium on Learning and Adaptive Behaviors for Robotic Systems
Neural Plasticity and Minimal Topologies for Reward-Based Learning
HIS '08 Proceedings of the 2008 8th International Conference on Hybrid Intelligent Systems
Spike-timing-dependent learning in memristive nanodevices
NANOARCH '08 Proceedings of the 2008 IEEE International Symposium on Nanoscale Architectures
Nonvolatile memristor memory: device characteristics and design implications
Proceedings of the 2009 International Conference on Computer-Aided Design
Synapsing Variable-Length Crossover: Meaningful Crossover for Variable-Length Genomes
IEEE Transactions on Evolutionary Computation
| Hi-index | 0.00 |
This paper presents a spiking neuro-evolutionary system which implements memristors as neuromodulatory connections, i.e. whose weights can vary during a trial. The evolutionary design process exploits parameter self-adaptation and a constructionist approach, allowing the number of neurons, connection weights, and inter-neural connectivity pattern to be evolved for each network. Additionally, each memristor has its own conductance profile, which alters the neuromodulatory behaviour of the memristor and may be altered during the application of the GA. We demonstrate that this approach allows the evolutionary process to discover beneficial memristive behaviours at specific points in the networks. We evaluate our approach against two phenomenological realworld memristive implementations, a theoretical "linear memristor", and a system containing standard connections only. Performance is evaluated on a simulated robotic navigation task.