The field of learning systems is broad and diverse, encompassing a large number of approaches such as artificial neural networks, genetic algorithms, evolutionary programming and intelligent agents. The underlying methods which are used to train such systems are equally diverse and draw from numerous fields including statistical reasoning, logic and signal processing. The strength of learning systems is that they can frequently provide solutions to problems which are too complex to be approached analytically. In such cases, learning systems can often find solutions which would take domain experts significant amounts of time to develop.
TRT (UK) has developed a strong capability in the area of learning systems and has knowledge and experience of practical implementations in:
Genetic Algorithms
Particle Swarm Optimisation
Artificial Neural Networks
This experience has been applied to a number of practical problems which includes traffic optimisation.