📄 neural networks for face recognition.htm
字号:
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<!-- saved from url=(0067)http://www-2.cs.cmu.edu/afs/cs.cmu.edu/user/mitchell/ftp/faces.html -->
<HTML><HEAD><TITLE>Neural Networks for Face Recognition</TITLE>
<META http-equiv=Content-Type content="text/html; charset=gb2312"><!-- Changed by: Tom Mitchell, 2-Mar-1997 -->
<META content="MSHTML 6.00.2600.0" name=GENERATOR></HEAD>
<BODY aLink=#5e5a80 bgColor=#eff7ff>
<H1>Neural Networks for Face Recognition </H1>
<H5>Companion to Chapter 4 of the textbook <A
href="http://www.cs.cmu.edu/~tom/mlbook.html">Machine Learning</A>. </H5>A
neural network learning algorithm called Backpropagation is among the most
effective approaches to machine learning when the data includes complex sensory
input such as images. This web page provides an implementation of the
Backpropagation algorithm described in Chapter 4 of the textbook <A
href="http://www.cs.cmu.edu/~tom/mlbook.html">Machine Learning</A>. It also
includes the dataset discussed in Section 4.7 of the book, containing over 600
face images.
<H3>Documentation</H3>This documentation is in the form of a homework assignment
(available in <A
href="http://www.cs.cmu.edu/afs/cs.cmu.edu/project/theo-8/faceimages/docs/hw97.ps">postscript
</A>or <A
href="http://www.cs.cmu.edu/afs/cs.cmu.edu/project/theo-8/faceimages/docs/hw97.tex">latex
</A>) that provides a step-by-step introduction to the code and data, and simple
instructions on how to run it.
<P>
<H3>Code</H3>The <A
href="http://www.cs.cmu.edu/afs/cs.cmu.edu/project/theo-8/faceimages/code">code
directory </A>contains the source code for the neural network Backpropagation
algorithm described in Chapter 4. (thanks to Jeff Shufelt for the initial
implementation.)
<H3>Data</H3>The <A
href="http://www.cs.cmu.edu/afs/cs.cmu.edu/project/theo-8/faceimages/faces">face
images directory </A>contains the face image data described in Chapter 4 of the
textbook. It is stored in PGM format. You can download a <A
href="http://www.cs.cmu.edu/afs/cs.cmu.edu/project/theo-8/faceimages/faces.tar.Z">compressed
tar file of all the images</A> (only ~10.5MB!), or a <A
href="http://www.cs.cmu.edu/afs/cs.cmu.edu/project/theo-8/faceimages/faces_4.tar.Z">compressed
tar file of only the one-quarter size images</A> (~0.5MB - most students used
only these images in order to save computation time). See the documentation
above for a full description of the images.
<P>The <A
href="http://www.cs.cmu.edu/afs/cs.cmu.edu/project/theo-8/faceimages/trainset">trainset
directory </A>contains the specifications of training and test sets referred to
in the documentation above.
<P><I>Visitors from outside CMU are invited to use this material free of charge
for any educational purpose, provided attribution is given in any lectures or
publications that make use of this material. </I>
<P><I>(<A href="http://www.cs.rug.nl/~peterkr/FACE/face.html"> another nice
source</A> of face images and code) </I>
<P></P></BODY></HTML>
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -