Results 181 to 190 of about 1,570 (213)

A Wavelet-based Encoding for Neuroevolution

Proceedings of the Genetic and Evolutionary Computation Conference 2016, 2016
A new indirect scheme for encoding neural network connection weights as sets of wavelet-domain coefficients is proposed in this paper. It exploits spatial regularities in the weight-space to reduce the genspace dimension by considering the low-frequency wavelet coefficients only.
Sjoerd van Steenkiste, Jan Koutník, Kurt Driessens, Jürgen Schmidhuber   +3 more
openaire   +3 more sources

On the significance of the permutation problem in neuroevolution

Proceedings of the 11th Annual conference on Genetic and evolutionary computation, 2009
In this paper we investigate the impact of the Permutation Problem on a standard Genetic Algorithm evolving neural networks for a difficult control problem. Through the use of Price's equation and an explicit enumeration of permutations within the population we demonstrate that for the given problem and representation the Permutation Problem is not as ...
Haflidason, Stefan, Neville, Richard
openaire   +2 more sources

The Neuroevolution of Consciousness

World Futures Review, 2015
Consciousness is the core of every living being and the key of human evolution. Consciousness is the core of the new paradigm now emerging in every field of science, culture, and spirituality. For centuries, consciousness has been divided from matter like the soul from the physical body.
openaire   +1 more source

Neuroevolution with NEAT

2020
NEAT is an algorithm that builds neural networks following an incremental and evolutionary process. It uses a genetic algorithm to evolve networks. In the very early generations, neural networks are very simple, composed of a few nodes and connections. However, complexity is added in each generation.
openaire   +1 more source

Surrogate-assisted neuroevolution

Proceedings of the Genetic and Evolutionary Computation Conference, 2022
Bryson Greenwood, Tyler McDonnell
openaire   +1 more source

Automatic feature selection in neuroevolution

Proceedings of the 7th annual conference on Genetic and evolutionary computation, 2005
Feature selection is the process of finding the set of inputs to a machine learning algorithm that will yield the best performance. Developing a way to solve this problem automatically would make current machine learning methods much more useful. Previous efforts to automate feature selection rely on expensive meta-learning or are applicable only when ...
Shimon Whiteson, Peter Stone 0001, Kenneth O. Stanley, Risto Miikkulainen, Nate Kohl   +4 more
openaire   +1 more source

Efficient Neuroevolution for a Quadruped Robot

2012
In this research, we investigate whether CoSyNE and CMA-NeuroES algorithms can efficiently optimize neural policy of a quadruped robot. Both of these algorithms are proven to optimize connection weights efficiently on Pole Balancing benchmark. Due to their good results on that benchmark, they are expected to be efficient on other control problems like ...
Shengbo Xu, Hirotaka Moriguchi, Shinichi Honiden   +2 more
openaire   +1 more source

Neuroevolution of hierarchical reservoir computers

Proceedings of the Genetic and Evolutionary Computation Conference, 2018
Reservoir Computers such as Echo State Networks (ESN) represent an alternative recurrent neural network model that provides fast training and state-of-the-art performances for supervised learning problems. Classic ESNs suffer from two limitations; hyperparameter selection and learning of multiple temporal and spatial scales.
openaire   +1 more source

Scalable Neuroevolution for Reinforcement Learning

2012
The idea of using evolutionary computation to train artificial neural networks, or neuroevolution (NE), has now been around for over 20 years. The main appeal of this approach is that, because it does not rely on gradient information (e.g. backpropagation), it can potentially harness the universal function approximation capability of neural networks to
openaire   +1 more source

Multiagent Learning through Neuroevolution

2012
Neuroevolution is a promising approach for constructing intelligent agents in many complex tasks such as games, robotics, and decision making. It is also well suited for evolving team behavior for many multiagent tasks. However, new challenges and opportunities emerge in such tasks, including facilitating cooperation through reward sharing and ...
Risto Miikkulainen, Eliana Feasley, Leif M. Johnson, Igor Karpov, Padmini Rajagopalan, Aditya Rawal, Wesley Tansey   +6 more
openaire   +1 more source