文件列表:

extract_features.m (1959, 2010-11-01)
kmeans_demo.m (3062, 2011-06-10)
minFunc (0, 2011-02-08)
minFunc\ArmijoBacktrack.m (3204, 2010-11-01)
minFunc\autoGrad.m (807, 2010-11-01)
minFunc\autoHess.m (901, 2010-11-01)
minFunc\autoHv.m (317, 2010-11-01)
minFunc\autoTensor.m (870, 2010-11-01)
minFunc\callOutput.m (378, 2010-11-01)
minFunc\conjGrad.m (1845, 2010-11-01)
minFunc\dampedUpdate.m (995, 2010-11-01)
minFunc\example_minFunc.m (2421, 2010-11-01)
minFunc\example_minFunc_LR.m (1604, 2010-11-01)
minFunc\isLegal.m (107, 2010-11-01)
minFunc\lbfgs.m (924, 2010-11-01)
minFunc\lbfgsC.c (2408, 2010-11-01)
minFunc\lbfgsC.mexa64 (7707, 2010-11-01)
minFunc\lbfgsC.mexglx (7733, 2010-11-01)
minFunc\lbfgsC.mexmac (9500, 2010-11-01)
minFunc\lbfgsC.mexmaci (12660, 2010-11-01)
minFunc\lbfgsC.mexmaci64 (8800, 2010-11-01)
minFunc\lbfgsC.mexw32 (7168, 2010-11-01)
minFunc\lbfgsC.mexw64 (9728, 2010-11-01)
minFunc\lbfgsUpdate.m (614, 2010-11-01)
minFunc\logistic (0, 2010-11-09)
minFunc\logistic\.svn (0, 2010-11-20)
minFunc\logistic\.svn\entries (1764, 2010-11-09)
minFunc\logistic\.svn\prop-base (0, 2010-11-09)
minFunc\logistic\.svn\prop-base\repmatC.dll.svn-base (53, 2010-11-09)
minFunc\logistic\.svn\prop-base\repmatC.mexglx.svn-base (53, 2010-11-09)
minFunc\logistic\.svn\prop-base\repmatC.mexmac.svn-base (53, 2010-11-09)
minFunc\logistic\.svn\props (0, 2010-11-09)
minFunc\logistic\.svn\text-base (0, 2010-11-09)
minFunc\logistic\.svn\text-base\LogisticDiagPrecond.m.svn-base (417, 2010-11-09)
minFunc\logistic\.svn\text-base\LogisticHv.m.svn-base (216, 2010-11-09)
minFunc\logistic\.svn\text-base\LogisticLoss.m.svn-base (669, 2010-11-09)
minFunc\logistic\.svn\text-base\mexutil.c.svn-base (1154, 2010-11-09)
minFunc\logistic\.svn\text-base\mexutil.h.svn-base (317, 2010-11-09)
minFunc\logistic\.svn\text-base\mylogsumexp.m.svn-base (227, 2010-11-09)
minFunc\logistic\.svn\text-base\repmatC.c.svn-base (3965, 2010-11-09)
... ...

K-means feature learning on CIFAR ---------------------------------- To run the demo, open kmeans_demo.m and modify the CIFAR_DIR variable to point to the directory containing your CIFAR training and test data. (These are the MATLAB files, which you can download from http://www.cs.toronto.edu/~kriz/cifar-10-matlab.tar.gz). Run matlab, change into the kmeans_demo directory and run "kmeans_demo". The script will print out the error on the test set when finished. Due to randomness in the K-means initialization, results may vary, but are generally > 77%. No cross-validation is done by this script -- the SVM regularization parameter is copied from the results obtained by our own validation on a random 80%/20% split of the training data. minFunc optimization package ---------------------------------- See: http://www.cs.ubc.ca/~schmidtm/Software/minFunc.html minFunc, written by Mark Schmidt, is included with this code. The minFunc license follows: "This software is made available under the Creative Commons Attribution-Noncommercial License. You are free to use, copy, modify, and re-distribute the work. However, you must attribute any re-distribution or adaptation in the manner specified below, and you may not use this work for commercial purposes without the permission of the author. Any re-distribution or adaptation of this work must contain the author's name and a link to the software's original webpage. For example, any re-distribution of the 'minFunc' software must contain a link to: http://www.cs.ubc.ca/~schmidtm/Software/minFunc.html This software comes with no guarantees, and all use of these codes is entirely at the user's own risk."

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：