HyperNEAT, which stands for Hypercube-based NeuroEvolution of Augmenting Topologies,
is a method for evolving indirectly-encoded artificial neural networks (ANNs) that was first …

Natural brains effectively integrate multiple sensory modalities and act upon the world
through multiple effector types. As researchers strive to evolve more sophisticated neural …

The robustness of animal behavior is unmatched by current machines, which often falter
when exposed to unforeseen conditions. While animals are notably reactive to changes in …

This position article argues that the sciences of the artificial (artificial intelligence and
artificial life) have a special relationship to art that is absent from much of science. Just as art …

An important challenge in neuroevolution is to evolve complex neural networks with multiple
modes of behavior. Indirect encodings can potentially answer this challenge. Yet in practice …

This paper demonstrates that compositional pattern producing networks (CPPNs) can
produce phenotypic patterns that exhibit fracture (ie discontinuities in patterns) and that …

Physics-based character animation offer an attractive alternative to traditional animation
techniques, however, physics-based approaches often struggle to incorporate active user …

Although it is uncommon that achievements in AI or alife are explicitly recognized for their
resonance with nature, there are some exceptions. Examples include John Conway's Game …

Across many scientific disciplines, there has emerged an open opportunity to utilize the
scale and reach of the Internet to collect scientific contributions from scientists and non …