Meta-NEAT, meta-analysis of neuroevolving topologies

Neural networks have gained a lot of attention recently and there have different techniques have been developed in order to evolve them. Neuroevolution is a flexible yet robust way of evolving such networks and it has been applied in a variety of fields from learning behaviour in games to solving classification problems. Neat is one of the most powerful approaches when it comes to neuroevolution. It can handle both behaviour learning as well as classification problems. The downside of neuroevolution is the time it takes to reach a solution as evolving both weights and structure comes at great costs. Meta-NEAT offers a way to optimize the convergence rate of NEAT through the use of an additional genetic algorithm built on top of NEAT. It adds an additional layer which learns optimal hyper-parameter configurations in order to boost the convergence rate of NEAT. The obtained configurations are thus useful as they both reveal the most important aspects of a network's evolution and greatly speed up the evolution process. The difficulties of crossing over in the context of neuroevolving topologies and a novel approach to it are also presented. The problems on which the approach was tested on range from behaviour learning problems to classification problems.