Application of neural networks to computer recipe prediction

Conventional mechanisms for computer colorant formulation commonly employ the Kubelka-Munk theory to relate reflectance values to colorant concentrations. However, there are situations where this approach is not applicable and hence an alternative is desirable. One such method is to utilize artificial intelligence techniques to mimic the behavior of the professional colorist. The purpose of this paper is to describe recent research being carried out at Reading University, sponsored by Courtaulds Research, that utilizes collections of cellular automata, known as neural networks, in the problem of recipe prediction.