A unified approach to evolving plasticity and neural geometry

@article{Risi2012AUA,
  title={A unified approach to evolving plasticity and neural geometry},
  author={Sebastian Risi and Kenneth O. Stanley},
  journal={The 2012 International Joint Conference on Neural Networks (IJCNN)},
  year={2012},
  pages={1-8}
}
  • S. RisiKenneth O. Stanley
  • Published 10 June 2012
  • Biology, Psychology
  • The 2012 International Joint Conference on Neural Networks (IJCNN)
An ambitious long-term goal for neuroevolution, which studies how artificial evolutionary processes can be driven to produce brain-like structures, is to evolve neurocontrollers with a high density of neurons and connections that can adapt and learn from past experience. Yet while neuroevolution has produced successful results in a variety of domains, the scale of natural brains remains far beyond reach. This paper unifies a set of advanced neuroevolution techniques into a new method called… 
View on IEEE
eplex.cs.ucf.edu
50 Citations
Highly Influential Citations
6
Background Citations
22
Methods Citations
12
Results Citations
3

Figures from this paper

50 Citations

Towards Evolving More Brain-Like Artificial Neural Networks

The combined approach, adaptive ES-HyperNEAT, unifies for the first time in neuroevolution the abilities to indirectly encode connectivity through geometry, generate patterns of heterogeneous plasticity, and simultaneously encode the density and placement of nodes in space.

Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks

Designing neural networks through neuroevolution

This Review looks at several key aspects of modern neuroevolution, including large-scale computing, the benefits of novelty and diversity, the power of indirect encoding, and the field’s contributions to meta-learning and architecture search.

Guided self-organization in indirectly encoded and evolving topographic maps

It is shown for the first time that the Hypercube-based NeuroEvolution of Augmenting Topologies (HyperNEAT) method can be seeded to begin evolution with such lateral connectivity, enabling genuine self-organizing dynamics.

Accelerating the Evolution of Cognitive Behaviors Through Human-Computer Collaboration

The recently introduced method novelty-assisted interactive evolution (NA-IEC), which combines human intuition with novelty search, allows the evolution of cognitive behaviors in a T-Maze domain faster than fully-automated searches by themselves.

Evolving Neural Turing Machines for Reward-based Learning

An evolvable version of the Neural Turing Machine (NTM) is introduced and it is shown that such an approach greatly simplifies the neural model, generalizes better, and does not require accessing the entire memory content at each time-step.

Evolving autonomous learning in cognitive networks

Markov Brains can incorporate feedback gates in such a way that they do not rely on an external objective feedback signal, but instead can generate internal feedback that is then used to learn, resulting in a more biologically accurate model of the evolution of learning.

A NEUROGENETIC ALGORITHM BASED ON RATIONAL AGENTS Ĺıdio

A biologically inspired NEA that evolves ANNs using these ideas as computational design techniques and the result is an optimized neural network architecture for solving classification problems.

Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity

It is shown for the first time that artificial neural networks with neuromodulated plastic LSTMs with millions of parameters can be trained with gradient descent, and concludes that differentiable neurmodulation of plasticity offers a powerful new framework for training neural networks.

Backpropamine : meta-training self-modifying neural networks with gradient descent

It is shown for the first time that artificial neural networks with such neuromodulated plasticity can be trained with gradient descent and improves the performance of neural networks on both reinforcement learning and supervised learning tasks.

References

SHOWING 1-10 OF 40 REFERENCES

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.

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.

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.

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.

Evolving plastic neural networks with novelty search

This article analyzes this inherent deceptiveness in a variety of different dynamic, reward-based learning tasks, and proposes a way to escape the deceptive trap of static policies based on the novelty search algorithm, which avoids deception entirely.

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 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.

A Taxonomy for Artificial Embryogeny

This taxonomy provides a unified context for long-term research in AE, so that implementation decisions can be compared and contrasted along known dimensions in the design space of embryogenic systems, and allows predicting how the settings of various AE parameters affect the capacity to efficiently evolve complex phenotypes.

Genetic Representation and Evolvability of Modular Neural Controllers

Experiments with plastic neural networks in a simple maze learning task indicate that adding a modular genetic representation to a state-of-the-art implicit neuroevolution method leads to better algorithm performance and increases the robustness of evolved solutions against detrimental mutations.

Competitive Coevolution through Evolutionary Complexification

It is argued that complexification, i.e. the incremental elaboration of solutions through adding new structure, achieves both these goals and is demonstrated through the NeuroEvolution of Augmenting Topologies (NEAT) method, which evolves increasingly complex neural network architectures.