Behavioural processes like those in sports, motor activities or rehabilitation are often the object of optimization methods. Such processes are often characterized by a complex structure. Measurements considering them may produce a huge amount of data. It is an interesting challenge not only to store these data, but also to transform them into useful information. Artificial Neural Networks turn out to be an appropriate tool to transform abstract numbers into informative patterns that help to understand complex behavioural phenomena. The contribution presents some basic ideas of neural network approaches and several examples of application. The aim is to give an impression of how neural methods can be used, especially in the field of sport.

Within the context of Artificial Life the question about the role of modularity has turned out to be crucial, especially with regard to the problem of evolvability. In order to be able to observe the development of modular structure, appro- priate modularity measures are important. We introduce a continuous measure based on information theory which can characterize the coupling among subsystems in a search prob- lem. In order to illustrate the concepts developed, they are applied to a very simple and intuitive set of combinatorial problems similar to scenarios used in the seminal work by Si- mon (1969). It is shown that this measure is closely related to the classification of search problems in terms of Separabil- ity, Non-Decomposability and Modular Interdependencyas introduced in (Watson and Pollack, 2005).

This article gives a short introduction to Self-Organizing Maps, a particular form of Artificial Neural Networks and shows by some examples, how these approaches can be used in order to analyze and visualize time series data originating from complex systems. The methods shown in this article have originally been developed for the analysis of RoboCup robot soccer games, a special kind of so-called Multi Agent Systems. Although this application has no direct connection to biomechanics, the examples shown here may give an impression of the abilities of Neural Networks in the field of Time Series Analysis in general. Because of the abstractness of the methods, it appears to be very likely that they can easily be adapted to Time Series Analysis problems within the biomechanics context.

The principle of modularization has proven to be extremely successful in the field of technical applications and particularly for Software Engineering purposes. The question to be answered within the present article is whether mechanisms can also be identified within the framework of Evolutionary Computation that cause a modularization of solutions. We will concentrate on processes, where modularization results only from the typical evolutionary operators, i.e. selection and variation by recombination and mutation (and not, e.g., from special modularization operators). This is what we call Self-Organized Modularization. Based on a combination of two formalizations by Radcliffe and Altenberg, some quantitative measures of modularity are introduced. Particularly, we distinguish Built-in Modularityas an inherent property of a genotype and Effective Modularity, which depends on the rest of the population. These measures can easily be applied to a wide range of present Evolutionary Computation models. It will be shown, both theoretically and by simulation, that under certain conditions, Effective Modularity (as defined within this paper) can be a selection factor. This causes Self-Organized Modularization to take place. The experimental observations emphasize the importance of Effective Modularityin comparison with Built-in Modularity. Although the experimental results have been obtained using a minimalist toy model, they can lead to a number of consequences for existing models as well as for future approaches. Furthermore, the results suggest a complex self-amplification of highly modular equivalence classes in the case of respected relations. Since the well-known Holland schemata are just the equivalence classes of respected relations in most Simple Genetic Algorithms, this observation emphasizes the role of schemata as Building Blocks (in comparison with arbitrary subsets of the search space).

The concept of modularity appears to be crucial for many questions in the field of Artificial Life research. However, there have not been many quantitative measures for modularity that are both general and viable. In this paper we introduce a measure for modularity based on information theory. Due to the generality of the information theory formalism, this measure can be applied to various problems and models; some connections to other formalisms are presented.

RoboCup is a most challenging project in the field of Artificial Intelligence and Multi-Agent Technology research. In this article, we will discuss some examples showing that RoboCup Simulation League scenarios can also be interesting in the interdisciplinary cooperation between computer science and sport science. One part of the paper concentrates on the generation of surrogate data which can be used in order to test data analysis methods. Furthermore, we will discuss RoboCup scenarios as testbed for sport theory as a future perspective.

Natural intelligence and autonomous agents face difficulties when acting in information-dense environments. Assailed by a multitude of stimuli they have to make sense of the inflow of information, filtering and processing what is necessary, but discarding that which is unimportant. This paper aims at investigating the interactions between evolution of the sensorial channel extracting the information from the environment and the simultaneous individual adaptation of agent-control. Our particular goal is to study the influence of learning on the evolution of sensors, with learning duration being the tunable parameter. A genetic algorithm governs the evolution of sensors appropriate for the agent solving a simple grid world task. The performance of the agent is taken as fitness; ‘sensors’ are conceived as a map from environmental states to agent observations, and individual adaptation is modeled by Q-learning. Our experimental results show that due to the principles of cognitive economy learning and varying the degree thereof actually transforms the fitness landscape. In particular we identify a trade-off between learning speed (load) and sensor accuracy (error). These results are further reinforced by theoretical analysis: we derive an analytical measure for the quality of sensors based on the mutual entropy between the system of states and the selection of an optimal action, a concept recently proposed by Polani, Martinetz, and Kim.

In this paper, we present an abstract model of sensor evolution, where sensor development is only determined by artificial evolution and the adaptation of agent reactions is accomplished by individual learning. With the environment cast into a MDP framework, sensors can be conceived as a map from environmental states to agent observations and Reinforcement Learning algorithms can be utilised. On the basis of a simple gridworld scenario, we present some results of the interaction between individual learning and evolution of sensors.

Within the context of Artificial Life the question about the role of modularity has turned out to be crucial, especially with regard to the problem of evolvability. In order to be able to observe the development of modular structure, appropriate modularity measures are important. We introduce a continuous measure based on information theory which can characterize the coupling among subsystems in a search problem. In order to illustrate the concepts developed, they are applied to a very simple and intuitive set of combinatorial problems similar to scenarios used in the seminal work by Simon (1969). It is shown that this measure is closely related to the classification of search problems in terms of Separability, Non-Decomposability and Modular Interdependency as introduced in (Watson and Pollack, 2005).