Towards a principled basis for the evaluation of hybrid cognitive architectures

In constructing hybrid systems, there is a need for a principled basis to determine the relative roles or functions of ANN and symbolic approaches. The primary objective of this work is the construction of a conceptual and methodological framework that permits an iterative sequence in which a hybrid model predicts the basis of cognitive performance and an objective analysis of performance provides empirical data evaluating and, thus, constraining the structure and processes of the model. The concept of 'semantic transparency' has been adopted since it can be used in analysing and describing both the characteristics of a model of cognition and the processes underlying human performance. An approach to the questions of evaluation is described based on empirical data obtained by brain monitoring of subjects during cognitive performance.<
>