?? neural networks for face recognition.mht
字號(hào):
From: <由 Windows Internet Explorer 7 保存>
Subject: Neural Networks for Face Recognition
Date: Tue, 29 Jan 2008 22:40:00 +0800
MIME-Version: 1.0
Content-Type: text/html;
charset="gb2312"
Content-Transfer-Encoding: quoted-printable
Content-Location: http://www.cs.cmu.edu/~tom/faces.html
X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.2180
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML><HEAD><TITLE>Neural Networks for Face Recognition</TITLE>
<META http-equiv=3DContent-Type content=3D"text/html; =
charset=3Dgb2312"><!-- Changed by: Tom Mitchell, 2-Mar-1997 -->
<META content=3D"MSHTML 6.00.5730.11" name=3DGENERATOR></HEAD>
<BODY aLink=3D#5e5a80 bgColor=3D#eff7ff>
<H1>Neural Networks for Face Recognition </H1>
<H5>Companion to Chapter 4 of the textbook <A=20
href=3D"http://www.cs.cmu.edu/~tom/mlbook.html">Machine Learning</A>. =
</H5>A=20
neural network learning algorithm called Backpropagation is among the =
most=20
effective approaches to machine learning when the data includes complex =
sensory=20
input such as images. This web page provides an implementation of the=20
Backpropagation algorithm described in Chapter 4 of the textbook <A=20
href=3D"http://www.cs.cmu.edu/~tom/mlbook.html">Machine Learning</A>. It =
also=20
includes the dataset discussed in Section 4.7 of the book, containing =
over 600=20
face images.=20
<H3>Documentation</H3>This documentation is in the form of a homework =
assignment=20
(available in <A=20
href=3D"http://www.cs.cmu.edu/afs/cs.cmu.edu/project/theo-8/faceimages/do=
cs/hw97.ps">postscript=20
</A>or <A=20
href=3D"http://www.cs.cmu.edu/afs/cs.cmu.edu/project/theo-8/faceimages/do=
cs/hw97.tex">latex=20
</A>) that provides a step-by-step introduction to the code and data, =
and simple=20
instructions on how to run it.
<P>
<H3>Code</H3>The <A=20
href=3D"http://www.cs.cmu.edu/afs/cs.cmu.edu/project/theo-8/faceimages/co=
de">code=20
directory </A>contains the source code for the neural network =
Backpropagation=20
algorithm described in Chapter 4. (thanks to Jeff Shufelt for the =
initial=20
implementation.)=20
<H3>Data</H3>The <A=20
href=3D"http://www.cs.cmu.edu/afs/cs.cmu.edu/project/theo-8/faceimages/fa=
ces">face=20
images directory </A>contains the face image data described in Chapter 4 =
of the=20
textbook. It is stored in PGM format. You can download a <A=20
href=3D"http://www.cs.cmu.edu/afs/cs.cmu.edu/project/theo-8/faceimages/fa=
ces.tar.Z">compressed=20
tar file of all the images</A> (only ~10.5MB!), or a <A=20
href=3D"http://www.cs.cmu.edu/afs/cs.cmu.edu/project/theo-8/faceimages/fa=
ces_4.tar.Z">compressed=20
tar file of only the one-quarter size images</A> (~0.5MB - most students =
used=20
only these images in order to save computation time). See the =
documentation=20
above for a full description of the images.
<P>The <A=20
href=3D"http://www.cs.cmu.edu/afs/cs.cmu.edu/project/theo-8/faceimages/tr=
ainset">trainset=20
directory </A>contains the specifications of training and test sets =
referred to=20
in the documentation above.=20
<P><I>Visitors from outside CMU are invited to use this material free of =
charge=20
for any educational purpose, provided attribution is given in any =
lectures or=20
publications that make use of this material. </I>
<P><I>(<A href=3D"http://www.cs.rug.nl/~peterkr/FACE/face.html"> another =
nice=20
source</A> of face images and code) </I>
<P></P></BODY></HTML>
?? 快捷鍵說明
復(fù)制代碼
Ctrl + C
搜索代碼
Ctrl + F
全屏模式
F11
切換主題
Ctrl + Shift + D
顯示快捷鍵
?
增大字號(hào)
Ctrl + =
減小字號(hào)
Ctrl + -