Computer Vision Research: The deep “depression”

Re:Computer Vision Research: The deep “depression” by suchow on Thursday June 09, 2016 @05:30AM (#11868340)

You might find this 1996 Nature paper by Olshausen & Field interesting. In it, they describe how a coding strategy that maximizes spareness when representing natural scenes is enough to produce a family of localized, oriented, bandpass receptive fields, like those found in the early visual system of humans.

https://courses.cs.washington.edu/courses/cse528/11sp/Olshau...

[ Parent | on HN ]

Re:Computer Vision Research: The deep “depression” by argonaut on Thursday June 09, 2016 @12:41PM (#11870532)

This fits in with my point: they imposed several restrictions about the model space: maximizing sparseness, and they also make several linearity assumptions.

[ Parent | on HN ]

Re:Computer Vision Research: The deep “depression” by happycube on Thursday June 09, 2016 @12:38PM (#11870510)

Superficially, those graphics look a lot like visualizations of conv nets.

[ Parent | on HN ]

Re:Computer Vision Research: The deep “depression” by trhway on Thursday June 09, 2016 @02:11PM (#11871191)

those papers should be, if not 101, at least 201 for neural net track as it would help to establish common framework and basis for thinking, talking and analysis of neural nets machinery.

[ Parent | on HN ]

Re:Computer Vision Research: The deep “depression” by eli_gottlieb on Thursday June 09, 2016 @12:51PM (#11870586)

Great, now I've got another paper to cite. Thanks!

[ Parent | on HN ]