[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Gzz-commits] gzz/Documentation/Manuscripts/Paper paper.tex
From: |
Tuomas J. Lukka |
Subject: |
[Gzz-commits] gzz/Documentation/Manuscripts/Paper paper.tex |
Date: |
Tue, 19 Nov 2002 15:35:17 -0500 |
CVSROOT: /cvsroot/gzz
Module name: gzz
Changes by: Tuomas J. Lukka <address@hidden> 02/11/19 15:35:13
Modified files:
Documentation/Manuscripts/Paper: paper.tex
Log message:
movestuff
CVSWeb URLs:
http://savannah.gnu.org/cgi-bin/viewcvs/gzz/gzz/Documentation/Manuscripts/Paper/paper.tex.diff?tr1=1.39&tr2=1.40&r1=text&r2=text
Patches:
Index: gzz/Documentation/Manuscripts/Paper/paper.tex
diff -u gzz/Documentation/Manuscripts/Paper/paper.tex:1.39
gzz/Documentation/Manuscripts/Paper/paper.tex:1.40
--- gzz/Documentation/Manuscripts/Paper/paper.tex:1.39 Tue Nov 19 15:19:39 2002
+++ gzz/Documentation/Manuscripts/Paper/paper.tex Tue Nov 19 15:35:10 2002
@@ -205,6 +205,25 @@
if all circles were green and all squares yellow, a considerable amount of
bits would be wasted.
+To understand why it is possible to learn to discriminate particular
+textures easily, consider the task of learning {\em one} texture.
+This is a two-class problem.
+Extensive literature...
+Here,
+there are two categories: the paper A and everything else.
+This problem is quite easy to solve: the probability of error
+decreases exponentially in the number of features.
+
+
+A perceptron\cite{XXX} is a simple neural network with XXX.
+In the input layer, various features are activated,
+... linear combination of features.
+
+Easy to learn when many features, STRICT CORRELATION
+
+$m$ binary features, $N$ vectors. Probability that
+
+
Easiest to remember presence and absence of features; therefore, should have
relatively small basis size, not to have too many features. XXX why?
@@ -685,30 +704,6 @@
4 textures, texture shading. These correspond to G400, GeForce2 and
GeForce3.
-\section{Experiment}
-
-\section{A neurocomputing interpretation}
-
-The recognizability of the generated textures is perhaps surprising
-in the light of the experiments on XXX..
-
-To understand why it is possible to learn to discriminate particular
-textures easily, consider the task of learning {\em one} texture.
-This is a two-class problem.
-Extensive literature...
-Here,
-there are two categories: the paper A and everything else.
-This problem is quite easy to solve: the probability of error
-decreases exponentially in the number of features.
-
-
-A perceptron\cite{XXX} is a simple neural network with XXX.
-In the input layer, various features are activated,
-... linear combination of features.
-
-Easy to learn when many features, STRICT CORRELATION
-
-$m$ binary features, $N$ vectors. Probability that
\section{Conclusions}
- [Gzz-commits] gzz/Documentation/Manuscripts/Paper paper.tex, Tuomas J. Lukka, 2002/11/15
- [Gzz-commits] gzz/Documentation/Manuscripts/Paper paper.tex, Tuomas J. Lukka, 2002/11/15
- [Gzz-commits] gzz/Documentation/Manuscripts/Paper paper.tex, Tuomas J. Lukka, 2002/11/15
- [Gzz-commits] gzz/Documentation/Manuscripts/Paper paper.tex, Tuomas J. Lukka, 2002/11/15
- [Gzz-commits] gzz/Documentation/Manuscripts/Paper paper.tex, Tuomas J. Lukka, 2002/11/15
- [Gzz-commits] gzz/Documentation/Manuscripts/Paper paper.tex, Tuomas J. Lukka, 2002/11/15
- [Gzz-commits] gzz/Documentation/Manuscripts/Paper paper.tex, Janne V. Kujala, 2002/11/16
- [Gzz-commits] gzz/Documentation/Manuscripts/Paper paper.tex, Janne V. Kujala, 2002/11/18
- [Gzz-commits] gzz/Documentation/Manuscripts/Paper paper.tex, Janne V. Kujala, 2002/11/18
- [Gzz-commits] gzz/Documentation/Manuscripts/Paper paper.tex,
Tuomas J. Lukka <=
- [Gzz-commits] gzz/Documentation/Manuscripts/Paper paper.tex, Janne V. Kujala, 2002/11/19
- [Gzz-commits] gzz/Documentation/Manuscripts/Paper paper.tex, Tuomas J. Lukka, 2002/11/19
- [Gzz-commits] gzz/Documentation/Manuscripts/Paper paper.tex, Janne V. Kujala, 2002/11/20
- [Gzz-commits] gzz/Documentation/Manuscripts/Paper paper.tex, Tuomas J. Lukka, 2002/11/20
- [Gzz-commits] gzz/Documentation/Manuscripts/Paper paper.tex, Tuomas J. Lukka, 2002/11/20
- [Gzz-commits] gzz/Documentation/Manuscripts/Paper paper.tex, Janne V. Kujala, 2002/11/20
- [Gzz-commits] gzz/Documentation/Manuscripts/Paper paper.tex, Janne V. Kujala, 2002/11/20
- [Gzz-commits] gzz/Documentation/Manuscripts/Paper paper.tex, Tuomas J. Lukka, 2002/11/22
- [Gzz-commits] gzz/Documentation/Manuscripts/Paper paper.tex, Tuomas J. Lukka, 2002/11/22
- [Gzz-commits] gzz/Documentation/Manuscripts/Paper paper.tex, Tuomas J. Lukka, 2002/11/22