Mercurial > ift6266

comparison writeup/nips2010_submission.tex @ 503:a0e820f04f8e

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
-
author Yoshua Bengio <bengioy@iro.umontreal.ca>
date Tue, 01 Jun 2010 13:53:05 -0400
parents 2b35a6e5ece4
children a41a8925be70 8bf07979b8ba
comparison
equal deleted inserted replaced
502:2b35a6e5ece4 503:a0e820f04f8e
197 $\alpha = \sqrt[3]{complexity} \times 10.0$ and $\sigma = 10 - 7 \times 197 $\alpha = \sqrt[3]{complexity} \times 10.0$ and $\sigma = 10 - 7 \times
198 \sqrt[3]{complexity}$.\\ 198 \sqrt[3]{complexity}$.\\
199 {\bf Pinch.} 199 {\bf Pinch.}
200 This GIMP filter is named "Whirl and 200 This GIMP filter is named "Whirl and
201 pinch", but whirl was set to 0. A pinch is ``similar to projecting the image onto an elastic 201 pinch", but whirl was set to 0. A pinch is ``similar to projecting the image onto an elastic
202 surface and pressing or pulling on the center of the surface''~\citep{GIMP-manual}. 202 surface and pressing or pulling on the center of the surface'' (GIMP documentation manual).
203 For a square input image, think of drawing a circle of 203 For a square input image, think of drawing a circle of
204 radius $r$ around a center point $C$. Any point (pixel) $P$ belonging to 204 radius $r$ around a center point $C$. Any point (pixel) $P$ belonging to
205 that disk (region inside circle) will have its value recalculated by taking 205 that disk (region inside circle) will have its value recalculated by taking
206 the value of another "source" pixel in the original image. The position of 206 the value of another "source" pixel in the original image. The position of
207 that source pixel is found on the line that goes through $C$ and $P$, but 207 that source pixel is found on the line that goes through $C$ and $P$, but
331 the best SDA (again according to validation set error), along with a precise estimate 331 the best SDA (again according to validation set error), along with a precise estimate
332 of human performance obtained via Amazon's Mechanical Turk (AMT) 332 of human performance obtained via Amazon's Mechanical Turk (AMT)
333 service\footnote{http://mturk.com}. 333 service\footnote{http://mturk.com}.
334 AMT users are paid small amounts 334 AMT users are paid small amounts
335 of money to perform tasks for which human intelligence is required. 335 of money to perform tasks for which human intelligence is required.
336 Mechanical Turk has been used extensively in natural language 336 Mechanical Turk has been used extensively in natural language processing and vision.
337 processing \citep{SnowEtAl2008} and vision 337 %processing \citep{SnowEtAl2008} and vision
338 \citep{SorokinAndForsyth2008,whitehill09}. 338 %\citep{SorokinAndForsyth2008,whitehill09}.
339 %\citep{SorokinAndForsyth2008,whitehill09}.
339 AMT users where presented 340 AMT users where presented
340 with 10 character images and asked to type 10 corresponding ASCII 341 with 10 character images and asked to type 10 corresponding ASCII
341 characters. They were forced to make a hard choice among the 342 characters. They were forced to make a hard choice among the
342 62 or 10 character classes (all classes or digits only). 343 62 or 10 character classes (all classes or digits only).
343 Three users classified each image, allowing 344 Three users classified each image, allowing