It is becoming increasingly apparent that without some form of
explanation capability, the full potential of trained artificial neural
networks (ANNs) may not be realised. This seminar gives an overview of
techniques developed to redress this situation. Specifically the seminar
focuses on mechanisms, procedures, and algorithms designed to insert
knowledge into ANNs (knowledge initialisation), extract rules from
trained ANNs (rule extraction), and utilise ANNs to refine existing
rule bases (rule refinement). The seminar also introduces a new taxonomy
for classifying the various techniques, discusses their modus operandi,
and delineates criteria for evaluating their efficacy. Results from
experiments using compositional rule-extraction from recurrent neural
networks trained on spoken language (children's dialogues) are discussed
in detail.