TY - GEN

T1 - Identifying the information contained in a flawed theory

AU - Engelson, Sean P

AU - Koppel, M.

N1 - Place of conference:USA

PY - 1996

Y1 - 1996

N2 - One common approach to using a prior domain
theory as a learning bias is to revise
the theory in accordance with a set of training
examples. More recently, another class
of methods has arisen in which the theory
is reinterpreted, either by probabilizing it,
or by using its components in constructive
induction. Revision-based methods tend to
work best when
aws in the given theory are
localized, whereas reinterpretation methods
tend to work well when
aws are distributed
evenly throughout the theory. This paper
describes a `meta-learning' algorithm which,
given a
awed domain theory, determines the
general nature of the theory's
aws by analyzing
the information
ow in the theory.
The method works by frst `probabilizing' the
theory, and then selectively `de-probabilizing'
components, based on the theory's performance
on a preclassifed set of training examples.
This method distinguishes between
those parts of the theory which should be interpreted
as given and those which need to
be revised or reinterpreted. This allows us
to directly determine the nature of the information
contained in the theory, and hence to
exploit the theory in the best way possible.

AB - One common approach to using a prior domain
theory as a learning bias is to revise
the theory in accordance with a set of training
examples. More recently, another class
of methods has arisen in which the theory
is reinterpreted, either by probabilizing it,
or by using its components in constructive
induction. Revision-based methods tend to
work best when
aws in the given theory are
localized, whereas reinterpretation methods
tend to work well when
aws are distributed
evenly throughout the theory. This paper
describes a `meta-learning' algorithm which,
given a
awed domain theory, determines the
general nature of the theory's
aws by analyzing
the information
ow in the theory.
The method works by frst `probabilizing' the
theory, and then selectively `de-probabilizing'
components, based on the theory's performance
on a preclassifed set of training examples.
This method distinguishes between
those parts of the theory which should be interpreted
as given and those which need to
be revised or reinterpreted. This allows us
to directly determine the nature of the information
contained in the theory, and hence to
exploit the theory in the best way possible.

UR - https://scholar.google.co.il/scholar?q=Identifying+the+Information+Contained+in+a+Flawed+Theory+&btnG=&hl=en&as_sdt=0%2C5

M3 - Conference contribution

BT - ICML

ER -