Hyper NEAT
Hypercube-based NEAT, or HyperNEAT, is a generative encoding that evolves artificial neural networks (ANNs) with the principles of the widely used NeuroEvolution of Augmented Topologies (NEAT) algorithm. It is a novel technique for evolving large-scale neural networks utilizing the geometric regularities of the task domain. It uses Compositional Pattern Producing Networks (CPPNs), which are used to generate the images for Picbreeder.org and shapes for EndlessForms.com.
Read more about Hyper NEAT: Applications To Date
Famous quotes containing the word neat:
“Photographs may be more memorable than moving images because they are a neat slice of time, not a flow. Television is a stream of underselected images, each of which cancels its predecessor. Each still photograph is a privileged moment, turned into a slim object that one can keep and look at again.”
—Susan Sontag (b. 1933)