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:
“Why should the generations overlap one another at all? Why cannot we be buried as eggs in neat little cells with ten or twenty thousand pounds each wrapped round us in Bank of England notes, and wake up, as the Sphinx wasp does, to find that its papa and mamma have not only left ample provision at its elbow but have been eaten by sparrows some weeks before we began to live consciously on our own accounts?”
—Samuel Butler (1835–1902)