English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

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

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