Mercurial > ift6266
annotate writeup/techreport.tex @ 403:a11692910312
Undoing some unwanted changes
author | humel |
---|---|
date | Wed, 28 Apr 2010 11:30:37 -0400 |
parents | 4c840798d290 |
children | fe2e2964e7a3 |
rev | line source |
---|---|
379
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
1 \documentclass[12pt,letterpaper]{article} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
2 \usepackage[utf8]{inputenc} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
3 \usepackage{graphicx} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
4 \usepackage{times} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
5 \usepackage{mlapa} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
6 |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
7 \begin{document} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
8 \title{Generating and Exploiting Perturbed Training Data for Deep Architectures} |
381 | 9 \author{The IFT6266 Gang} |
379
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
10 \date{April 2010, Technical Report, Dept. IRO, U. Montreal} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
11 |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
12 \maketitle |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
13 |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
14 \begin{abstract} |
392
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
15 Recent theoretical and empirical work in statistical machine learning has |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
16 demonstrated the importance of learning algorithms for deep |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
17 architectures, i.e., function classes obtained by composing multiple |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
18 non-linear transformations. In the area of handwriting recognition, |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
19 deep learning algorithms |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
20 had been evaluated on rather small datasets with a few tens of thousands |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
21 of examples. Here we propose a powerful generator of variations |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
22 of examples for character images based on a pipeline of stochastic |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
23 transformations that include not only the usual affine transformations |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
24 but also the addition of slant, local elastic deformations, changes |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
25 in thickness, background images, color, contrast, occlusion, and |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
26 various types of pixel and spatially correlated noise. |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
27 We evaluate a deep learning algorithm (Stacked Denoising Autoencoders) |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
28 on the task of learning to classify digits and letters transformed |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
29 with this pipeline, using the hundreds of millions of generated examples |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
30 and testing on the full NIST test set. |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
31 We find that the SDA outperforms its |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
32 shallow counterpart, an ordinary Multi-Layer Perceptron, |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
33 and that it is better able to take advantage of the additional |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
34 generated data. |
379
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
35 \end{abstract} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
36 |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
37 \section{Introduction} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
38 |
392
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
39 Deep Learning has emerged as a promising new area of research in |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
40 statistical machine learning (see~\emcite{Bengio-2009} for a review). |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
41 Learning algorithms for deep architectures are centered on the learning |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
42 of useful representations of data, which are better suited to the task at hand. |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
43 This is in great part inspired by observations of the mammalian visual cortex, |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
44 which consists of a chain of processing elements, each of which is associated with a |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
45 different representation. In fact, |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
46 it was found recently that the features learnt in deep architectures resemble |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
47 those observed in the first two of these stages (in areas V1 and V2 |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
48 of visual cortex)~\cite{HonglakL2008}. |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
49 Processing images typically involves transforming the raw pixel data into |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
50 new {\bf representations} that can be used for analysis or classification. |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
51 For example, a principal component analysis representation linearly projects |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
52 the input image into a lower-dimensional feature space. |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
53 Why learn a representation? Current practice in the computer vision |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
54 literature converts the raw pixels into a hand-crafted representation |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
55 (e.g.\ SIFT features~\cite{Lowe04}), but deep learning algorithms |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
56 tend to discover similar features in their first few |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
57 levels~\cite{HonglakL2008,ranzato-08,Koray-08,VincentPLarochelleH2008-very-small}. |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
58 Learning increases the |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
59 ease and practicality of developing representations that are at once |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
60 tailored to specific tasks, yet are able to borrow statistical strength |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
61 from other related tasks (e.g., modeling different kinds of objects). Finally, learning the |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
62 feature representation can lead to higher-level (more abstract, more |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
63 general) features that are more robust to unanticipated sources of |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
64 variance extant in real data. |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
65 |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
66 Whereas a deep architecture can in principle be more powerful than a shallow |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
67 one in terms of representation, depth appears to render the training problem |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
68 more difficult in terms of optimization and local minima. |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
69 It is also only recently that |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
70 successful algorithms were proposed to overcome some of these |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
71 difficulties. |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
72 |
379
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
73 \section{Perturbation and Transformation of Character Images} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
74 |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
75 \subsection{Affine Transformations} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
76 \subsection{Adding Slant} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
77 \subsection{Local Elastic Deformations} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
78 \subsection{Changing Thickness} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
79 \subsection{Occlusion} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
80 \subsection{Background Images} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
81 \subsection{Salt and Pepper Noise} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
82 \subsection{Spatially Gaussian Noise} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
83 \subsection{Color and Contrast Changes} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
84 |
393
4c840798d290
added examples of figure and table of results
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
392
diff
changeset
|
85 \begin{figure}[h] |
4c840798d290
added examples of figure and table of results
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
392
diff
changeset
|
86 \resizebox{.99\textwidth}{!}{\includegraphics{images/example_t.png}}\\ |
4c840798d290
added examples of figure and table of results
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
392
diff
changeset
|
87 \caption{Illustration of the pipeline of stochastic |
4c840798d290
added examples of figure and table of results
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
392
diff
changeset
|
88 transformations applied to the image of a lower-case t |
4c840798d290
added examples of figure and table of results
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
392
diff
changeset
|
89 (the upper left image). Each image in the pipeline (going from |
4c840798d290
added examples of figure and table of results
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
392
diff
changeset
|
90 left to right, first top line, then bottom line) shows the result |
4c840798d290
added examples of figure and table of results
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
392
diff
changeset
|
91 of applying one of the modules in the pipeline. The last image |
4c840798d290
added examples of figure and table of results
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
392
diff
changeset
|
92 (bottom right) is used as training example.} |
4c840798d290
added examples of figure and table of results
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
392
diff
changeset
|
93 \label{fig:pipeline} |
4c840798d290
added examples of figure and table of results
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
392
diff
changeset
|
94 \end{figure} |
379
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
95 |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
96 \section{Learning Algorithms for Deep Architectures} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
97 |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
98 \section{Experimental Setup} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
99 |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
100 \subsection{Training Datasets} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
101 |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
102 \subsubsection{Data Sources} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
103 |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
104 \begin{itemize} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
105 \item {\bf NIST} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
106 \item {\bf Fonts} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
107 \item {\bf Captchas} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
108 \item {\bf OCR data} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
109 \end{itemize} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
110 |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
111 \subsubsection{Data Sets} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
112 \begin{itemize} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
113 \item {\bf NIST} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
114 \item {\bf P07} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
115 \item {\bf NISTP} {\em ne pas utiliser PNIST mais NISTP, pour rester politically correct...} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
116 \end{itemize} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
117 |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
118 \subsection{Models and their Hyperparameters} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
119 |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
120 \subsubsection{Multi-Layer Perceptrons (MLP)} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
121 |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
122 \subsubsection{Stacked Denoising Auto-Encoders (SDAE)} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
123 |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
124 \section{Experimental Results} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
125 |
392
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
126 \subsection{SDA vs MLP} |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
127 |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
128 \begin{center} |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
129 \begin{tabular}{lcc} |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
130 & train w/ & train w/ \\ |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
131 & NIST & P07 + NIST \\ \hline |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
132 SDA & & \\ \hline |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
133 MLP & & \\ \hline |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
134 \end{tabular} |
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
135 \end{center} |
379
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
136 |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
137 \subsection{Perturbed Training Data More Helpful for SDAE} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
138 |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
139 \subsection{Training with More Classes than Necessary} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
140 |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
141 \section{Conclusions} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
142 |
392
5f8fffd7347f
possible image for illustrating perturbations
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
381
diff
changeset
|
143 \bibliography{strings,ml,aigaion} |
379
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
144 \bibliographystyle{mlapa} |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
145 |
a21a174c1c18
added writeup skeleton
Yoshua Bengio <bengioy@iro.umontreal.ca>
parents:
diff
changeset
|
146 \end{document} |