Explorer What has learning got to do with expert systems ?

General rights Copyright for the publications made accessible via the Edinburgh Research Explorer is retained by the author(s) and / or other copyright owners and it is a condition of accessing these publications that users recognise and abide by the legal requirements associated with these rights. Take down policy The University of Edinburgh has made every reasonable effort to ensure that Edinburgh Research Explorer content complies with UK legislation. If you believe that the public display of this file breaches copyright please contact [email protected] providing details, and we will remove access to the work immediately and investigate your claim. I am grateful for feedback and suggestions from Richard Young and Bernard Sliver. This paper was prepared as an invited talk on learning for the first workshop on expert systems of the IKBS section of the Alvey Programme. It discusses: the significance of learning for expert systems, the tools available and the medium term goals of learning research. This discussion centres around ..r.ule and concept learning. It concludes that the significance of automatic knowledge acquisition may have been overstated, but that there are other significant applications of learning in expert systems. The tradeoffs between classification and focussing based learning systems are discussed and some of the outstanding problems are listed, especially the dependence on human provision of the description space and the potential for combinatorial explosions.