Capabilities of Thoughtful Machines

Article type: Research Article

Authors: Kalyanasundaram, Bala | Velauthapillai, Mahe

Affiliations: Computer Science Dept., Georgetown University, Washington, D.C., USA. E-mail: {kalyan,mahe}@cs.georgetown.edu

Abstract: When learning a concept the learner produces conjectures about the concept he learns. Typically the learner contemplates, performs some experiments, make observations, does some computation, thinks carefully (that is not output a new conjecture for a while) and then makes a conjecture about the (unknown) concept. Any new conjecture of an intelligent learner should be valid for at least some "reasonable amount of time" before some evidence is found that the conjecture is false. Then maybe the learner can further study and explore the concept more and produce a new conjecture that again will be valid for some "reasonable amount of time". In this paper we formalize the idea of reasonable amount of time. The learners who obey the above constraint are called "Thoughtful learners" (TEX learners). We show that there are classes that can be learned using the above model. We also compare this leaning paradigm to other existing ones. The surprising result is that there is no capability intervals in team TEX-type learning. On the other hand, capability intervals exist in all other models. Also these learners are orthogonal to the learners that have been studied in the literature.

Keywords: Inductive Inference, mind changes, errors, thoughtful machines

Journal: Fundamenta Informaticae, vol. 74, no. 2-3, pp. 329-340, 2006