Guided self-organization in indirectly encoded and evolving topographic maps

  title={Guided self-organization in indirectly encoded and evolving topographic maps},
  author={Sebastian Risi and Kenneth O. Stanley},
  journal={Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation},
  • S. RisiKenneth O. Stanley
  • Published 12 July 2014
  • Computer Science
  • Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation
An important phenomenon seen in many areas of biological brains and recently in deep learning architectures is a process known as self-organization. For example, in the primary visual cortex, color and orientation maps develop based on lateral inhibitory connectivity patterns and Hebbian learning dynamics. These topographic maps, which are found in all sensory systems, are thought to be a key factor in enabling abstract cognitive representations. This paper shows for the first time that the… 

Figures and Tables from this paper

Multiagent System for Layer Free Network

A multiagent system that have feedforward networks as its subset while free from layer structure with matrix-vector scheme is proposed that is an effective approach for developing more biologically plausible model while preserving compatibility with deep networks to alternate units with multiple agents.

Evolutionary neural networks for deep learning: a review

This study conducted a systematic review of the literature on ENNs by using the PRISMA protocol and introduced the main research techniques in terms of connection weights, architecture design and learning rules, and the existing research results are summarized.

Neuroevolution in Games: State of the Art and Open Challenges

  • S. RisiJ. Togelius
  • Computer Science
    IEEE Transactions on Computational Intelligence and AI in Games
  • 2017
This paper surveys research on applying neuroevolution to games along five different axes, which are the role NE is chosen to play in a game, the different types of neural networks used, the way these networks are evolved, how the fitness is determined and what type of input the network receives.

The nature of primary consciousness. A new synthesis

A Systematic Literature Review of the Successors of “NeuroEvolution of Augmenting Topologies”

A systematic literature review (SLR) is presented to list and categorize the methods succeeding NEAT and proposes a new categorization scheme of NEAT's successors into three clusters.



Cooperative self-organization of afferent and lateral connections in cortical maps

LISSOM demonstrates how self-organization can bootstrap based on input information only, without global supervision or predetermined lateral interaction, and can potentially account for the development of multiple maps of different modalities on the same undifferentiated cortical architecture.

Autonomous Evolution of Topographic Regularities in Artificial Neural Networks

This letter shows that when geometry is introduced to evolved ANNs through the hypercube-based neuroevolution of augmenting topologies algorithm, they begin to acquire characteristics that indeed are reminiscent of biological brains.

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.

A Hypercube-Based Encoding for Evolving Large-Scale Neural Networks

The main conclusion is that the ability to explore the space of regular connectivity patterns opens up a new class of complex high-dimensional tasks to neuroevolution.

A Hypercube-Based Indirect Encoding for Evolving Large-Scale Neural Networks

The main conclusion is that the ability to explore the space of regular connectivity patterns opens up a new class of complex high-dimensional tasks to neuroevolution.

An Enhanced Hypercube-Based Encoding for Evolving the Placement, Density, and Connectivity of Neurons

ES-HyperNEAT significantly expands the scope of neural structures that evolution can discover by automatically deducing the node geometry from implicit information in the pattern of weights encoded by HyperNEAT, thereby avoiding the need to evolve explicit placement.

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.

A unified approach to evolving plasticity and neural geometry

The most interesting aspect of this investigation is that the emergent neural structures are beginning to acquire more natural properties, which means that neuroevolution can begin to pose new problems and answer deeper questions about how brains evolved that are ultimately relevant to the field of AI as a whole.

The development of topography in the visual cortex: a review of models.

This article reviews the models of topographic organization in the visual cortex in a roughly historical sequence, beginning with von der Malsburg's paper 1973 paper in Kybernetik on self-organization of orientation selectivity.

Self-Organizing Process Based On Lateral Inhibition And Synaptic Resource Redistribution

Self-organizing feature maps are usually implemented by abstracting the low-level neural and parallel distributed processes, but the process is somewhat hampered by boundary e ects and the parameters need to be carefully evolved.