ABSTRACT
The theoretical roots of the approach of an artificial simulation by means of neural networks lie back in the 1940s. Meanwhile, the claim of modelling biological dynamics has been reduced to a more pragmatic application of the great abilities of net-based concepts and tools. Today, two approaches are mainly in use. They can complement each other, in particular in decision making processes that occur in team sports. Unsupervised or self-organizing maps or networks (SOM) can learn and recognize the patterns of match situations on their own (Figure 11.1, left graphic), whereas supervised or feed forward networks (FFN) can learn by supervision what are the best solutions for a situation, once recognized (Figure 11.1, right graphic; see also Kohonen 1995; Hopfield 1982). (left) Self-organizing map (SOM: neurons are grouped to clusters which form the output; (right) feed-forward network (FFN): comparison of expected output O<sub>exp</sub> and computed output O<sub>comp</sub> is feedback and so changes the neuron connections to minimize the difference between expected and computed output https://s3-euw1-ap-pe-df-pch-content-public-p.s3.eu-west-1.amazonaws.com/9780203134610/da870a77-c7b8-499b-a206-296ee96364fa/content/9780415809702_fig011_1_B.jpg" xmlns:xlink="https://www.w3.org/1999/xlink"/>
