Showing papers on "Active learning (machine learning) published in 1984"

Deductive Learning [and Discussion]

Abstract: A non-technical discussion of a new approach to the problem of concept learning in the context of artificial devices is given. Learning is viewed as a process of acquiring a program for recognizing a concept from an environment that does not reveal an explicit description of the program but only suggests it by such means as identifying positive examples of it. The proposed model makes possible a study of learning that reconciles three requirements: the classes of concepts that can be learnt are relevant for general purpose knowledge; they can be characterized; the process of learning them is computationally feasible.

Rough-sets based learning systems

Abstract: Let us now make the final conclusions concerning the learning processes in static and expanding systems. In a static system we are able to approximate a new concept and teach the system only that approximation. The relation between the concept and its approximation is stored as a system rule. In an expanding system we can teach the system the exact concept. Concepts learned by the system are used to approximate concepts which have to be learned. In static systems these approximations are replaced by larger approximations by applying system rules. For this reason the number of examples used by the teacher to teach a concept in static systems is greater than the number of examples needed to teach the same concept in expanding systems.

The Learning Process — A Model Based on an Engineering Approach

Abstract: A model is presented for analysing the learning activity through an engineering approach. The main components are: input (raw data), elaborational phase (data processing), output (processed data) and conditions of learning (bias). The components are interconnected in a closed loop feedback pattern, including ‘impedance matching’ to optimise the learning process.