HackerPapers

arXiv:1003.0358cs.NE

Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition

Dan Claudiu Ciresan, Ueli Meier, Luca Maria Gambardella, Juergen Schmidhuber

Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.

Abstract

Good old on-line back-propagation for plain multi-layer perceptrons yields a very low 0.35% error rate on the famous MNIST handwritten digits benchmark. All we need to achieve this best result so far are many hidden layers, many neurons per layer, numerous deformed training images, and graphics cards to greatly speed up learning.

arXiv comments
14 pages, 2 figures, 4 listings
Journal reference
Neural Computation, Volume 22, Number 12, December 2010
DOI
doi:10.1162/NECO_a_00052
Subjects
cs.NENeural and Evolutionary Computing cs.AIArtificial Intelligence

On Hacker News

Linked by 1 identifiable commenter in 1 comment across 1 thread, from Jan 2015 to Jan 2015.

Comments linking this paper, per year.

Discussed in comments1 thread

  1. On Artificial Intelligence 1 comment

    • In any case, I think that's a point very much relevant to the analogy: when you do more of the same, but at a scale a few orders of magnitude larger, you do get qualitatively different results. That's very much applicable to AI. As an illustration, when we started to use GPUs…

      fcholletView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.