News for hackers. Stuff that matters.

A comment on All of Statistics, by Larry Wassserman (2013) [pdf]. Parent comment

Re:All of Statistics, by Larry Wassserman (2013) [pdf] by eli_gottlieb on Sunday May 15, 2016 @11:50PM (#11704125)
>There are lots of neural network applications that have little to do with statistics (image recognition with convolutional neural networks for example).

You're kidding, right? The most fundamental reasons that deep convnets work at all are statistical in nature.

[ Parent | on HN ]
Re:All of Statistics, by Larry Wassserman (2013) [pdf] by niels_olson on Monday May 16, 2016 @12:38AM (#11704276)
Well, yes and no. It's like saying you need to understand Bernoulli's priciple before designing the SR-71. True, but 7 levels short of where you're working.
[ Parent | on HN ]