PADO: A New Learning Architecture for Object
Recognition
A. Teller, and M. Veloso. Symbolic Visual Learning, Oxford University Press, (1996)
Abstract
Most artificial intelligence systems today work on
simple problems and artificial domains because they
rely on the accurate sensing of the task world. Object
recognition is a crucial part of the sensing challenge
and machine learning stands in a position to catapult
object recognition into real world domains. Given that,
to date, machine learning has not delivered general
object recognition, we propose a different point of
attack: the learning architectures themselves. We have
developed a method for directly learning and combining
algorithms in a new way that imposes little burden on
or bias from the humans involved. This learning
architecture, PADO, and the new results it brings to
the problem of natural image object recognition is the
focus of this chapter.
%0 Book Section
%1 teller:1995:PADO
%A Teller, Astro
%A Veloso, Manuela
%B Symbolic Visual Learning
%D 1996
%E Ikeuchi, Katsushi
%E Veloso, Manuela
%I Oxford University Press
%K algorithms, genetic memory programming,
%P 81--116
%T PADO: A New Learning Architecture for Object
Recognition
%U http://www.cs.cmu.edu/afs/cs/usr/astro/public/papers/PADO.ps
%X Most artificial intelligence systems today work on
simple problems and artificial domains because they
rely on the accurate sensing of the task world. Object
recognition is a crucial part of the sensing challenge
and machine learning stands in a position to catapult
object recognition into real world domains. Given that,
to date, machine learning has not delivered general
object recognition, we propose a different point of
attack: the learning architectures themselves. We have
developed a method for directly learning and combining
algorithms in a new way that imposes little burden on
or bias from the humans involved. This learning
architecture, PADO, and the new results it brings to
the problem of natural image object recognition is the
focus of this chapter.
@incollection{teller:1995:PADO,
abstract = {Most artificial intelligence systems today work on
simple problems and artificial domains because they
rely on the accurate sensing of the task world. Object
recognition is a crucial part of the sensing challenge
and machine learning stands in a position to catapult
object recognition into real world domains. Given that,
to date, machine learning has not delivered general
object recognition, we propose a different point of
attack: the learning architectures themselves. We have
developed a method for directly learning and combining
algorithms in a new way that imposes little burden on
or bias from the humans involved. This learning
architecture, PADO, and the new results it brings to
the problem of natural image object recognition is the
focus of this chapter.},
added-at = {2008-06-19T17:46:40.000+0200},
author = {Teller, Astro and Veloso, Manuela},
biburl = {https://www.bibsonomy.org/bibtex/2e29dae51bf55fbc401170016a55c499b/brazovayeye},
booktitle = {Symbolic Visual Learning},
editor = {Ikeuchi, Katsushi and Veloso, Manuela},
interhash = {187edcf97a05851c280ffe1603f26b87},
intrahash = {e29dae51bf55fbc401170016a55c499b},
keywords = {algorithms, genetic memory programming,},
notes = {This is NOT the same as \cite{TechTeller}. The overlap
is about 20 of the 34 pages but it is different
enough},
pages = {81--116},
publisher = {Oxford University Press},
size = {34 pages},
timestamp = {2008-06-19T17:53:01.000+0200},
title = {{PADO}: {A} New Learning Architecture for Object
Recognition},
url = {http://www.cs.cmu.edu/afs/cs/usr/astro/public/papers/PADO.ps},
year = 1996
}