HyperNEAT: The first five years
HyperNEAT, which stands for Hypercube-based NeuroEvolution of Augmenting Topologies,
is a method for evolving indirectly-encoded artificial neural networks (ANNs) that was first …
is a method for evolving indirectly-encoded artificial neural networks (ANNs) that was first …
An enhanced hypercube-based encoding for evolving the placement, density, and connectivity of neurons
S Risi, KO Stanley - Artificial life, 2012 - direct.mit.edu
Intelligence in nature is the product of living brains, which are themselves the product of
natural evolution. Although researchers in the field of neuroevolution (NE) attempt to …
natural evolution. Although researchers in the field of neuroevolution (NE) attempt to …
Ca-neat: evolved compositional pattern producing networks for cellular automata morphogenesis and replication
Cellular Automata (CA) are a remarkable example of morphogenetic system, where cells
grow and self-organize through local interactions. CA have been used as abstractions of …
grow and self-organize through local interactions. CA have been used as abstractions of …
Evolving the placement and density of neurons in the hyperneat substrate
The Hypercube-based NeuroEvolution of Augmenting Topologies (HyperNEAT) approach
demonstrated that the pattern of weights across the connectivity of an artificial neural …
demonstrated that the pattern of weights across the connectivity of an artificial neural …
NEAT in HyperNEAT substituted with genetic programming
In this paper we present application of genetic programming (GP)[1] to evolution of indirect
encoding of neural network weights. We compare usage of original HyperNEAT algorithm …
encoding of neural network weights. We compare usage of original HyperNEAT algorithm …
Scalable multiagent learning through indirect encoding of policy geometry
DB D'Ambrosio, KO Stanley - Evolutionary Intelligence, 2013 - Springer
Multiagent systems present many challenging, real-world problems to artificial intelligence.
Because it is difficult to engineer the behaviors of multiple cooperating agents by hand …
Because it is difficult to engineer the behaviors of multiple cooperating agents by hand …
Artificial biochemical networks: Evolving dynamical systems to control dynamical systems
Biological organisms exist within environments in which complex nonlinear dynamics are
ubiquitous. They are coupled to these environments via their own complex dynamical …
ubiquitous. They are coupled to these environments via their own complex dynamical …
Critical factors in the performance of HyperNEAT
TG van den Berg, S Whiteson - … of the 15th annual conference on …, 2013 - dl.acm.org
HyperNEAT is a popular indirect encoding method for evolutionary computation that has
performed well on a number of benchmark tasks. This paper presents a series of …
performed well on a number of benchmark tasks. This paper presents a series of …
Automatically evolving a general controller for robot swarms
Controller design is an important problem for swarm robotics. Although many successful
controllers have been proposed, most are hand-coded, sometimes using adaptive …
controllers have been proposed, most are hand-coded, sometimes using adaptive …
Evolving neural fields for problems with large input and output spaces
We have developed an extension of the NEAT neuroevolution method, called NEATfields, to
solve problems with large input and output spaces. The NEATfields method is a multilevel …
solve problems with large input and output spaces. The NEATfields method is a multilevel …