The modularity in freeform evolving neural networks

@article{Li2011TheMI,
  title={The modularity in freeform evolving neural networks},
  author={Shuguang Li and Jianping Yuan},
  journal={2011 IEEE Congress of Evolutionary Computation (CEC)},
  year={2011},
  pages={2605-2610}
}
In this paper, we validate whether the network modularity can emerge, and the evolution performance can be improved by varying the environment or evolution process under a more freeform artificial evolution. Previous studies have demonstrated that the modular structure naturally arisen as a response of the variations on environment and selection process, however, since the models they used were relatively simple and with some biasing constraints, the results may lack of generality. In contrast… 

Figures and Tables from this paper

Encouraging networks modularity by seeding motifs

The results indicate that modularity could be encouraged under certain conditions and networks were able to build networks meeting a desired Z-score.

Modularity as a Solution to Spatial Interference in Neural Networks

Modularity is an architectural trait that is prominent in biological neural networks, but strangely absent in evolved artificial neural networks. This report contains the results of a theoretical ...

References

SHOWING 1-10 OF 16 REFERENCES

Noise and the Evolution of Neural Network Modularity

This article evolves nonlinear artificial neural network classifiers for a binary classification task with a modular structure when noise is added to the edge weights of the networks, and modular network topologies evolve, even without representational support.

Investigating whether hyperNEAT produces modular neural networks

The first documented case of HyperNEAT producing a modular phenotype is presented, but the inability to encourage modularity on harder problems where modularity would have been beneficial suggests that more work is needed to increase the likelihood that Hyper NEAT and similar algorithms produce modular ANNs in response to challenging, decomposable problems.

Constraining connectivity to encourage modularity in HyperNEAT

This paper investigates how altering the traditional approach to determining whether connections are expressed in HyperNEAT influences modularity, and provides an important clue to how an indirect encoding of network structure can be encouraged to evolve modularity.

ON THE ORIGIN OF MODULAR VARIATION

It is suggested, using simple computer simulations, that modularity arises spontaneously in evolutionary systems in response to variation, and that the amount of modular separation is logarithmically proportional to the rate of variation.

An evolutionary algorithm that constructs recurrent neural networks

It is argued that genetic algorithms are inappropriate for network acquisition and an evolutionary program is described, called GNARL, that simultaneously acquires both the structure and weights for recurrent networks.

Forming Neural Networks Through Efficient and Adaptive Coevolution

The symbiotic adaptive neuroevolution system coevolves a population of neurons that cooperate to form a functioning neural network to be more efficient and more adaptive and to maintain higher levels of diversity than the more common network-based population approaches.

The binary-weights neural network for robot control

The results show that through evolutionary learning, this novel RNN controller can handle nonlinear problems as well as common RNN even without adjustable weights and has the simplicity, usability and potential for robot control.

Complex Adaptations and the Evolution of Evolvability

It is proposed that the genotype-phenotype map can evolve by two main routes: epistatic mutations, or the creation of new genes.

Neuroevolution: from architectures to learning

This paper gives an overview of the most prominent methods for evolving ANNs with a special focus on recent advances in the synthesis of learning architectures.

Evolving Artificial Neural Networks

It is shown, through a considerably large literature review, that combinations between ANN’s and EA’’ can lead to significantly better intelligent systems than relying on ANNs or EA”s alone.