An overview is given of the role and relevance of Artificial Neural Nets (ANNs) as control systems for autonomous agents. Though ANNs can be used as computational input/output devices, cognition requires not this but rather some method of implementing dynamical systems. A wider class of ANNs incorporating temporal dynamics and feedback is presented as one way to achieve this. These are difficult to design and evolutionary approaches are a possible approach. Since
evolving complex robot controllers inevitably takes a long time, one can not aff ord to start afresh with each new problem, and an incremental adaptation approach will be necessary in the long term. This means that standard o ff-the-shelf optimising genetic algorithms are not appropriate unless adjusted to their new role.
I. Harvey (1997): Cognition is not Computation: Evolution is not Optimisation. In Artificial Neural Networks – ICANN97, Gerstner, W., Germond, A., Hasler, M, and Nicoud, J-D (eds). Springer-Verlag LNCS 1327 (1997) pp. 685-690. ISBN: 3540636315 Proc. of 7th International Conference on Artificial Neural Networks, 7-10 October 1997, Lausanne, Switzerland.
