We present a method for evolving and implementing artificial neural networks (ANNs) on Field Programmable Analog Arrays (FPAAs). These FPAAs offer the small size and low power usa...
Abstract. Q-learning can be used to learn a control policy that maximises a scalar reward through interaction with the environment. Qlearning is commonly applied to problems with d...
Chris Gaskett, David Wettergreen, Alexander Zelins...
We propose Merge Growing Neural Gas (MGNG) as a novel unsupervised growing neural network for time series analysis. MGNG combines the state-of-the-art recursive temporal context of...
Andreas Andreakis, Nicolai von Hoyningen-Huene, Mi...
Artificial intelligence techniques have found a number of applications in hypermedia, mostly in two specific areas, user interface, particularly adaptive ones and information sear...
— The first-person-shooter Quake II is used as a platform to test neuro-visual control and retina input layouts. Agents are trained to shoot a moving enemy as quickly as possibl...