probably approximately correct learning

Probably approximately correct learning (PAC learning) is a framework of learning that was proposed by Leslie Valiant in his paper A theory of the learnable. In this framework the learner gets samples that are classified according to a function from a certain class. The aim of the learner is to find an approximation of the function with high probability. We demand the learner to be able to learn the concept given any arbitrary approximation ratio, probability of success or distribution of the samples. The model was further extended to treat noise (misclassified samples). The PAC framework allowed accurate mathematical analysis of learning. PAC learning framework is part of computational learning theory.

References

L. Valiant. A theory of the learnable. Communications of the ACM, 27, 1984. The paper that proposed the PAC learning framework.
M. Kearns, U. Vazirani. An Introduction to Computational Learning Theory. MIT Press, 1994. A textbook.

External link

Probably Approximately Correct Learning - excellent introduction to the topic

<< Previous

Word Browser

Next >>

qotd
hvz spa
list of australian test batsmen who have scored over 5000 test runs
cottabus
gametek
birmingham pub bombings
john covode
hans makart
hepes
lateral geniculate nucleus
giant depolarizing potentials

prussian tribute
geniculate nucleus
prenatal
postnatal
de vlaamse leeuw
in utero
in situ
moel fammau
morgue
dall's porpoise
fulbert of chartres

own goal
the estonian state decorations
the order of the cross of terra mariana
origin systems
the order of the estonian red cross
the time ships
evolution (stephen baxter)
naruto jutsus
the military order of the cross of the eagle
the order of the cross of the eagle
it feels like thunder

who ate all the pies?
the order of the white star
guanent
americans for democratic action
worthington
itasca
new cumberland
the order of the national coat of arms
galway (disambiguation)
stratford, connecticut
cuvier's beaked whale