Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition — mentioned by fchollet

Thu, 22 Jan 2015 02:01:16 GMT

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 for training neural nets with the exact same algorithms as a decade earlier but with an order of magnitude more parameters, we got dramatically better results (see Ciresan et al. 2010 [1]). Building the same dumb skyscrapers but making them 100 times taller might in fact get them to fly. [1] http://arxiv.org/abs/1003.0358

Paper and discussion history. A mention is not an endorsement.

Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition · HackerPapers discussions

Deep Big Simple Neural Nets Excel on Handwritten Digit Recognition — mentioned by fchollet