Information Filtering: Selection Mechanisms in Learning Systems
Shaul Markovitch and Paul Scott. Information Filtering: Selection Mechanisms in Learning Systems. Machine Learning, 10:113-151 1993.
Abstract
Knowledge has traditionally been considered to have a beneficial effect on the performance of problem solvers but recent studies indicate that knowledge acquisition is not necessarily a monotonically beneficial process, because additional knowledge sometimes leads to a deterioration in system performance. This paper is concerned with the problem of harmful knowledge: that is, knowledge whose removal would improve a system's performance. In the first part of the paper a unifying framework, called the information filtering model, is developed to define the various alternative methods for eliminating such knowledge from a learning system. This framework identifies five locations in the information flow of a learning system where selection processes, called filters, may be inserted to remove potentially harmful knowledge. These filters are termed selective experience, selective attention, selective acquisition, selective retention, and selective utilization. The framework can be used by developers of learning systems as a guide for selecting an appropriate filter to reduce or eliminate harmful knowledge. In the second part of the paper, the framework is used to identify a suitable filter for solving a problem caused by the acquisition of harmful knowledge in a learning system called LASSY. LASSY is a system that improves the performance of a PROLOG interpreter by utilizing acquired domain specific knowledge in the form of lemmas stating previously proved results. It is shown that the particular kind of problems that arise with this system are best solved using a novel utilization filter that blocks the use of lemmas in attempts to prove subgoals that have a high probability of failing.
Keywords: Selective Learning, Utility Problem, Speedup Learning, Lemma Learning
Secondary Keywords:
Online version:
Bibtex entry:
@article{Markovitch:1993:IFS,
Author = {Shaul Markovitch and Paul Scott},
Title = {Information Filtering: Selection Mechanisms in Learning Systems},
Year = {1993},
Journal = {Machine Learning},
Volume = {10},
Number = {2},
Pages = {113--151},
Url = {http://www.cs.technion.ac.il/~shaulm/papers/pdf/Markovitch-Scott-mlj1993.pdf},
Keywords = {Selective Learning, Utility Problem, Speedup Learning, Lemma Learning},
Secondary-keywords = {Harmful Knowledge, Information Filtering, Active Learning, Deductive Learning},
Abstract = {
Knowledge has traditionally been considered to have a beneficial
effect on the performance of problem solvers but recent studies
indicate that knowledge acquisition is not necessarily a
monotonically beneficial process, because additional knowledge
sometimes leads to a deterioration in system performance. This
paper is concerned with the problem of harmful knowledge: that is,
knowledge whose removal would improve a system's performance. In
the first part of the paper a unifying framework, called the
information filtering model, is developed to define the various
alternative methods for eliminating such knowledge from a learning
system. This framework identifies five locations in the
information flow of a learning system where selection processes,
called filters, may be inserted to remove potentially harmful
knowledge. These filters are termed selective experience,
selective attention, selective acquisition, selective retention,
and selective utilization. The framework can be used by developers
of learning systems as a guide for selecting an appropriate filter
to reduce or eliminate harmful knowledge. In the second part of
the paper, the framework is used to identify a suitable filter for
solving a problem caused by the acquisition of harmful knowledge
in a learning system called LASSY. LASSY is a system that improves
the performance of a PROLOG interpreter by utilizing acquired
domain specific knowledge in the form of lemmas stating previously
proved results. It is shown that the particular kind of problems
that arise with this system are best solved using a novel
utilization filter that blocks the use of lemmas in attempts to
prove subgoals that have a high probability of failing.
}
}