Neuroevolution: from architectures to learning

@article{Floreano2008NeuroevolutionFA,
  title={Neuroevolution: from architectures to learning},
  author={Dario Floreano and Peter D{\"u}rr and Claudio Mattiussi},
  journal={Evolutionary Intelligence},
  year={2008},
  volume={1},
  pages={47-62}
}
Artificial neural networks (ANNs) are applied to many real-world problems, ranging from pattern classification to robot control. In order to design a neural network for a particular task, the choice of an architecture (including the choice of a neuron model), and the choice of a learning algorithm have to be addressed. Evolutionary search methods can provide an automatic solution to these problems. New insights in both neuroscience and evolutionary biology have led to the development of… 

Evolving neural networks

Methods that evolve fixed-topology networks, network topologies, and network construction processes, ways of combining traditional neural network learning algorithms with evolutionary methods, and applications of neuroevolution to control, robotics, artificial life, and games are reviewed.

Evolving Neural Networks

Methods that evolve fixed-topology networks, network topologies, and network construction processes, ways of combining traditional neural network learning algorithms with evolutionary methods, and applications of neuroevolution to control, robotics, artificial life, and games are reviewed.

Evolving neural networks

Methods that evolve fixed-topology networks, network topologies, and network construction processes, ways of combining traditional neural network learning algorithms with evolutionary methods, and applications of neuroevolution to control, robotics, artificial life, and games are reviewed.

Evolving neural networks

Evolving neural networks

Methods that evolve fixed-topology networks, network topologies, and network construction processes, ways of combining traditional neural network learning algorithms with evolutionary methods, and applications of neuroevolution to game playing, robot control, resource optimization, and cognitive science are reviewed.

Evolving Artificial Neural Networks using Cartesian Genetic Programming

This thesis extends Cartesian Genetic Programming such that it can represent recurrent program structures allowing for the creation of recurrent Artificial Neural Networks and is demonstrated to be extremely competitive in the domain of series forecasting.

Structural and Parametric Evolution of Continuous-Time Recurrent Neural Networks

This work aims to extend a recent method known as NEAT to evolve continuous-time recurrent neural networks (CTRNNs) and reveals some advantages when evolving general CTRNNs over traditional models.

On the automated, evolutionary design of neural networks: past, present, and future

This work aims to provide a complete reference of all works related to neuroevolution of convolutional neural networks up to the date, and to the best of its knowledge, this is the best survey reviewing the literature in this field.

Indirectly Encoding Neural Plasticity as a Pattern of Local Rules

This paper aims to show that learning rules can be effectively indirectly encoded by extending the Hypercube-based NeuroEvolution of Augmenting Topologies (HyperNEAT) method to evolve large-scale adaptive ANNs, which is a major goal for neuroevolution.

Evolution of neural networks

This tutorial will review neuroevolution methods that evolve fixed-topology networks, network topologies, and network construction processes, ways of combining gradient-based training with evolutionary methods, and applications of these techniques in control, robotics, artificial life, games, image processing, and language.
...

References

SHOWING 1-10 OF 107 REFERENCES

Neuroevolution with Analog Genetic Encoding

This paper shows how AGE can be used to simultaneously evolve the topology and the weights of ANNs for complex control systems and shows that its performance is equivalent or superior to some of the most powerful algorithms for neuroevolution in the literature.

The evolution of learning algorithms for artificial neural networks

A neural network model in which weights between computational nodes are modiied according to a local learning rule is investigated and it is shown how learning behaviour emerges as a distributed property of the entire network.

Training Feedforward Neural Networks Using Genetic Algorithms

A set of experiments performed on data from a sonar image classification problem are described to illustrate the improvements gained by using a genetic algorithm rather than backpropagation and chronicle the evolution of the performance of the genetic algorithm as it added more and more domain-specific knowledge into it.

Neuroevolution for reinforcement learning using evolution strategies

  • C. Igel
  • Computer Science
    The 2003 Congress on Evolutionary Computation, 2003. CEC '03.
  • 2003
The CMA-ES is applied to the optimization of the weights of neural networks for solving reinforcement learning problems, and results with fixed network topologies are significantly better than those reported for the best evolutionary method so far.

Efficient reinforcement learning through symbiotic evolution

A new reinforcement learning method called SANE (Symbiotic, Adaptive Neuro-Evolution), which evolves a population of neurons through genetic algorithms to form a neural network capable of performing a task, is presented.

Evolving Neural Networks through Augmenting Topologies

A method is presented, NeuroEvolution of Augmenting Topologies (NEAT), which outperforms the best fixed-topology method on a challenging benchmark reinforcement learning task and shows how it is possible for evolution to both optimize and complexify solutions simultaneously.

The Evolution of Learning: An Experiment in Genetic Connectionism

Evolving Dynamical Neural Networks for Adaptive Behavior

It is demonstrated that continuous-time recurrent neural networks are a viable mechanism for adaptive agent control and that the genetic algorithm can be used to evolve effective neural controllers.

Evolving developing spiking neural networks

  • D. Federici
  • Computer Science
    2005 IEEE Congress on Evolutionary Computation
  • 2005
A plastic spiking neural network model, particularly suited for evolution and development, is introduced, testing its performance against direct encoding and results show similar conclusions regarding the improved scalability of the development system and its connection to regularity.

Evolving networks: using the genetic algorithm with connectionist learning

A survey of recent work that combines Holland's Genetic Algorithm with con-nectionist techniques and delineates some of the basic design problems these hybrids share concludes that the GA's global sampling characteristics compliment connectionist local search techniques well, leading to eecient and reliable hybrids.
...