The field of feature selection has many different competing algorithms, selection criteria and measure functions, with little theoretical justification for the choice of one measure over another. This thesis focuses on feature selection algorithms that use information theoretic criteria and provide a solid theoretical justification for their use. It also presents experimental results showing how the different factorisation assumptions affect classification performance.

Feature Selection Via Joint Likelihood

Computers & Technology

Pocock, Adam C.

Computer Science

See the best price to sell, buy, or rent books by Pocock, Adam C.. BookScouter helps to compare book prices from 25+ online bookstores and 30+ buyback vendors with a single search.

Books by Pocock, Adam C.

See the best price to sell, buy, or rent books by Pocock, Adam C.. BookScouter helps to compare book prices from 25+ online bookstores and 30+ buyback vendors with a single search.

Feature Selection Via Joint Likelihood