Video games provide an opportunity and challenge for the soft computational intelligence methods like the symbolic games did for “good old-fashioned artificial intelligence. ” This article reviews the achievements and future prospects of one particular approach, that of evolving neural networks, or neuroevolution. This approach can be used to construct adaptive characters in existing video games, and it can serve as a foundation for a new genre of games based on machine learning. Evolution can be guided by human knowledge, allowing the designer to control the kinds of solutions that emerge and encouraging behaviors that appear visibly intelligent to the human player. Such techniques may allow building video games that are more engaging and entertaining than current games, and those that can serve as training environments for people. Techniques developed in these games may also be widely applicable in other fields, such as robotics, resource optimization, and intelligent assistants. 1

Abstract. A fuzzy controller is usually designed by formulating the knowledge of a human expert into a set of linguistic variables and fuzzy rules. One of the most successful methods to automate the fuzzy controllers development process are evolutionary algorithms. In this work, we propose a so-called “approximative ” representation for fuzzy systems, where the antecedent of the rules are determined by a multivariate membership function defined in terms of Voronoi regions. Such representation guarantees the ɛ-completeness property and provides a synergistic relation between the rules. An evolutionary algorithm based on this representation can evolve all the components of the fuzzy system, and due to the properties of the representation, the algorithm (1) can benefit from the use of geometric genetic operators, (2) does not need genetic repair algorithms, (3) guarantees the completeness property and (4) can implement previous knowledge in a simple way by using adaptive a priori rules. The proposed representation is evaluated on an obstacle avoidance problem with a simulated mobile robot. 1

Abstract — Self-organization of connection patterns within brain areas of animals begins prenatally, and has been shown to depend on internally generated patterns of neural activity. The neural structures continue to develop postnatally through externally driven patterns, when the sensory systems are exposed to stimuli from the environment. The internally generated patterns have been proposed to give the neural system an appropriate bias so that it can learn reliably from complex environmental stimuli. This paper evaluates the hypothesis that complex artificial learning systems can benefit from a similar approach, consisting of initial training with patterns from an evolved pattern generator, followed by training with the actual training set. To test this hypothesis, competitive learning networks were trained for recognizing handwritten digits. The results demonstrate how the approach can improve learning performance by discovering the appropriate initial weight biases, thereby compensating for weaknesses of the learning algorithm. Because of the smaller evolutionary search space, this approach was also found to require much fewer generations than direct evolution of network weights. Since discovering the right biases efficiently is critical for solving large-scale problems with learning, these results suggest that internal training pattern generation is an effective method for constructing complex systems. Index Terms — Artificial neural networks, competitive learning, complex systems, evolutionary computation, pattern generator, self-organization, spontaneous activity I.