Exploiting Heavy Tails in Training Times of Multilayer Perceptrons: A Case Study with the UCI Thyroid Disease Database

Computer Science – Neural and Evolutionary Computing

Scientific paper

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

8 pages, 4 figures, submitted for consideration to the "Statistics and Its Interface" journal

Scientific paper

The random initialization of weights of a multilayer perceptron makes it possible to model its training process as a Las Vegas algorithm, i.e. a randomized algorithm which stops when some required training error is obtained, and whose execution time is a random variable. This modeling is used to perform a case study on a well-known pattern recognition benchmark: the UCI Thyroid Disease Database. Empirical evidence is presented of the training time probability distribution exhibiting a heavy tail behavior, meaning a big probability mass of long executions. This fact is exploited to reduce the training time cost by applying two simple restart strategies. The first assumes full knowledge of the distribution yielding a 40% cut down in expected time with respect to the training without restarts. The second, assumes null knowledge, yielding a reduction ranging from 9% to 23%.

No associations

LandOfFree

Say what you really think

Search LandOfFree.com for scientists and scientific papers. Rate them and share your experience with other people.

Rating

Exploiting Heavy Tails in Training Times of Multilayer Perceptrons: A Case Study with the UCI Thyroid Disease Database does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Exploiting Heavy Tails in Training Times of Multilayer Perceptrons: A Case Study with the UCI Thyroid Disease Database, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Exploiting Heavy Tails in Training Times of Multilayer Perceptrons: A Case Study with the UCI Thyroid Disease Database will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFWR-SCP-O-573778

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.