Mercurial > cortex

comparison org/literature-review.org @ 378:8e62bf52be59

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
reviewing ullman's stuff.
author Robert McIntyre <rlm@mit.edu>
date Thu, 11 Apr 2013 06:46:01 +0000
parents 80cd096682b2
children
comparison
equal deleted inserted replaced
377:80cd096682b2 378:8e62bf52be59
209 overfitting. 209 overfitting.
210 210
211 nifty, relevant, realistic ideas 211 nifty, relevant, realistic ideas
212 He doesn't confine himself to unplasaubile assumptions 212 He doesn't confine himself to unplasaubile assumptions
213 213
214 214 ** Our Reading
215 *** 2002 Visual features of intermediate complexity and their use in classification
216
217
215 218
216 219
217 ** Getting around the dumb "fixed training set" methods 220 ** Getting around the dumb "fixed training set" methods
218 221
219 *** 2006 Learning to classify by ongoing feature selection 222 *** 2006 Learning to classify by ongoing feature selection
247 The more complex models must be able to be initialized efficiently 250 The more complex models must be able to be initialized efficiently
248 from the less complex models which they replace! 251 from the less complex models which they replace!
249 252
250 253
251 ** Non Parametric Models 254 ** Non Parametric Models
252
253 *** 2002 Visual features of intermediate complexity and their use in classification
254
255
256 255
257 *** 2010 The chains model for detecting parts by their context 256 *** 2010 The chains model for detecting parts by their context
258 257
259 Like the constelation method for rigid objects, but extended to 258 Like the constelation method for rigid objects, but extended to
260 non-rigid objects as well. 259 non-rigid objects as well.
319 feature F proved effective for a similar class C in the past. 318 feature F proved effective for a similar class C in the past.
320 319
321 Allows you to trasfer the "gestalt" of a similiar class to a new 320 Allows you to trasfer the "gestalt" of a similiar class to a new
322 class, by adapting all the features of the learned class that have 321 class, by adapting all the features of the learned class that have
323 correspondance to the new class. 322 correspondance to the new class.
323
324 *** 2007 Semantic Hierarchies for Recognizing Objects and Parts
325
326 Better learning of complex objects like faces by learning each
327 piece (like nose, mouth, eye, etc) separately, then making sure
328 that the features are in plausable positions.