In the early days of computing it was often stated that computers could never exhibit “intelligence” because they could only carry out tasks that their programmers had anticipated and pre-programmed solutions for.
Advances in areas such as Artificial Intelligence, Machine Learning, Evolutionary Computation, Neural Networks, Data Mining and Automated Reasoning have shown that computers are capable of far more.
The Adaptive System Research Group (ASRG) researches and develops computational systems that are able to adapt to or learn from the data, knowledge or environment in which they are working. These systems typically mimic processes found in nature. We seek to develop computational systems that employ evolutionary, learning, optimisation and modelling techniques to solve or improve performance on complex problems.
Many problems faced by companies are impractical to solve by traditional analytical methods. Such problems may be computationally intractable, or may involve highly non-linear, complex systems. These difficulties offer no impediment to evolutionary algorithms. The Walking Fish Group focuses on such systems, their algorithms and the suitability of the proposed solutions.
As the name suggests, multi-agent systems are made up of multiple single agents. This allows them to provide solutions to problems that are inherently too complex or impractical for single agent systems.