http://wiki.nosdigitais.teia.org.br/index.php?title=Pattern_Theory_and_Applications_2013&feed=atom&action=historyPattern Theory and Applications 2013 - Histórico de revisão2024-03-29T06:49:40ZHistórico de revisões para esta página neste wikiMediaWiki 1.39.0http://wiki.nosdigitais.teia.org.br/index.php?title=Pattern_Theory_and_Applications_2013&diff=33414&oldid=prevV1z em 21h09min de 15 de setembro de 20142014-09-15T21:09:52Z<p></p>
<table style="background-color: #fff; color: #202122;" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="pt-BR">
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Edição anterior</td>
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Edição das 18h09min de 15 de setembro de 2014</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l1">Linha 1:</td>
<td colspan="2" class="diff-lineno">Linha 1:</td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>This is the main page of a graduate-level course in pattern theory, machine learning, pattern formation, pattern recognition and computer vision being taught in 2013/1 at the Polytechnic Institute [http://pt.wikipedia.org/wiki/IPRJ IPRJ]/UERJ. It is generally useful for computer scientists, statisticians, and applied mathematicians wishing to automatically model and analyze phenomena from sets of images and other signals. Think of this course as a special 'flavor' of artificial intelligence which has been largely developed at one of the instructor's ''alma mater'', Brown University, through researchers such as fields medalist David Mumford and Ulf Grenader.</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>This is the main page of a graduate-level course in pattern theory, machine learning, pattern formation, pattern recognition and computer vision being taught in 2013/1 at the Polytechnic Institute [http://pt.wikipedia.org/wiki/IPRJ IPRJ]/UERJ. It is generally useful for computer scientists, statisticians, and applied mathematicians wishing to automatically model and analyze phenomena from sets of images and other signals. Think of this course as a special 'flavor' of artificial intelligence which has been largely developed at one of the instructor's ''alma mater'', Brown University, through researchers such as fields medalist David Mumford and Ulf Grenader.</div></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>[[Image:Fruitflyembryo.jpg|right|300px]]</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>[[Image:Fruitflyembryo.jpg|right|300px]]</div></td></tr>
<tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;"></ins></div></td></tr>
<tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">'''This is the page of a 2013 course.'''</ins></div></td></tr>
<tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">* Link to the [[PT|most up-to-date course page]]</ins></div></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br/></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br/></td></tr>
<tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== General Info ==</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== General Info ==</div></td></tr>
</table>V1zhttp://wiki.nosdigitais.teia.org.br/index.php?title=Pattern_Theory_and_Applications_2013&diff=33411&oldid=prevV1z: 2013 archive2014-09-15T21:06:25Z<p>2013 archive</p>
<p><b>Página nova</b></p><div>This is the main page of a graduate-level course in pattern theory, machine learning, pattern formation, pattern recognition and computer vision being taught in 2013/1 at the Polytechnic Institute [http://pt.wikipedia.org/wiki/IPRJ IPRJ]/UERJ. It is generally useful for computer scientists, statisticians, and applied mathematicians wishing to automatically model and analyze phenomena from sets of images and other signals. Think of this course as a special 'flavor' of artificial intelligence which has been largely developed at one of the instructor's ''alma mater'', Brown University, through researchers such as fields medalist David Mumford and Ulf Grenader.<br />
[[Image:Fruitflyembryo.jpg|right|300px]]<br />
<br />
== General Info ==<br />
* Instructors: prof. Francisco Duarte Moura Neto, Ph.D. Berkeley, and prof. [http://www.lems.brown.edu/~rfabbri Ricardo Fabbri], Ph.D. Brown University<br />
* Meeting times: Tues 6pm-7:40pm, Weds 5pm - 6:40pm<br />
* Forum for file exchange and discussion: [http://uerj.tk uerj.tk]<br />
<br />
=== Course Format ===<br />
* Evaluation criteria: Final grade = projects (60%), class participation (20%) and exercises/reading summaries (20%)<br />
* Each student will have a main project to develop throughout the semester<br />
** There will be mid and final project presentations, each worth 50% of the project grade<br />
* There will be assigned lab exercises and reading almost every class (papers, book chapters, etc)<br />
** Readings must be summarized with '''personal opinions and reflexions''' and a summary must be typed and handed in<br />
** Discussion and coding in class will be graded as "class participation"<br />
** '''Bring your laptops on Wednesdays!'''<br />
<br />
=== Pre-requisites ===<br />
* Undergraduate-level mathematics and probability (will review as needed)<br />
* Intermediate programming experience with any numerics scripting language such as Scilab, Python, R or Matlab.<br />
<br />
== Approximate Content ==<br />
We will be reading sections of interest from Mumford's book together with complements from the others.<br />
Focus may shift based on research demand and demand from student's individual projects.<br />
We plan to focus on the following topics.<br />
<br />
#Overview of Pattern Theory, Machine Learning, Pattern Recognition, Computer Vision and Image Understanding. Motivation. Basic concepts.<br />
#Character Recognition and Syntactic Grouping. Image Understanding. (chapter 3)<br />
#Image Texture, Image Segmentation and Gibbs Models (ch. 4)<br />
#'''Faces and Flexible Templates''' (ch. 5): '''--> Focus of course <--'''<br />
#Natural Scenes and their Multiscale Analysis (ch. 6)<br />
#Catastrophe Theory - readings from Rene Thom's book. Qualitative pattern theory?<br />
<br />
== Main Resources ==<br />
<br />
=== Textbooks ===<br />
* Main book: ''Pattern Theory: The Stochastic Analysis of Real-World Signals'', David Mumford and Agnes Desolneux (see [http://uerj.tk uerj.tk]) [[Image:Mumford-book.jpg]]<br />
<video type="vimeo" id="65784108" width="552" height="470" allowfullscreen="true" desc="Pattern Theory Chapter 0 Screen Reading: [http://vimeo.com/65784108 vimeo.com/65784108]"/><br />
<video type="youtube" id="-8H_v6njHmw" width="552" height="450" frame="true" allowfullscreen="true" desc="David Mumford's Lecture 1 at IMPA/Brazil - research topic similar to ch 5 of the book"/><br />
<video type="youtube" id="IxLX4_z0_hg" width="552" height="450" frame="true" allowfullscreen="true" desc="David Mumford's Lecture 2 at IMPA/Brazil - research topic similar to ch 5 of the book"/><br />
<br />
* ''Pattern Theory: From Representation to Inference'', Ulf Grenader<br />
* ''Structural Stability and Morphogenesis'', Rene Thom. We'll be complementing the course with ideas from this book, looking into this for investigating pattern formation<br />
<br />
=== Lectures ===<br />
<br />
<br />
==== Partial listing & Tentative Outline ====<br />
'''Part I Chapters 0 and 1 - pattern theory overview and intro to its basic methods through text processing'''<br />
# Overview of pattern theory and classic pattern recognition<br />
# The classical paradigm - machine learning, pattern recognition systems, clustering, recognition, and how it all fits together: the design of the ultimate AI system<br />
# Scilab and Matlab exercises - simulating everything with <tt>rand()</tt><br />
# Reviewing probability theory guided by Ch 1's first exercises<br />
# Overview of the Bayesian approach to machine learning<br />
# Probabilistic models for text processing - unraveling Ch 1 sec. 0, part I<br />
# Probabilistic models for text processing - unraveling Ch 1 sec. 0, part II<br />
# Practical programming of Ch 1 sec. 0 (frequency tables and sampling of conditional probabilities for text synthesis), guided by Ch 1's Exercise section 5 (p. 55)<br />
# Markov Chains - main definitions and concepts of convergence<br />
# Mutual Information, Entropies, Kullback-Leibler distances<br />
# Word Boundaries Machine Translation<br />
# Practical programming of Ch 1 - DNA Sequence statistics, p. 56 ex 6<br />
# [http://wiki.nosdigitais.teia.org.br/Imagem:Aula-pagerank.pdf Extra lecture on Markov Chains - Google PageRank and markov chains for organizing large networks and machine learning]<br />
'''Part II of Course: lets jump to Chapter 5: Flexible Templates'''<br />
# Overview of manifolds, differential geometry of surfaces and higher dimensions<br />
# Bird's eye view of Mumford's research on diffeomorphisms and infinite dimensional differential goemetry<br />
## See Mumford's presentations (on the right)<br />
## Infinite dimensional nonlinear manifolds and their applications to shape were already predicted by Riemann: ''"There are however manifolds in which the fixing of position requires not a finite number but either an infinite series or a continuous manifold of determinations of quantity. Such manifolds are constituted for example by ... the possible shapes of a figure in space, etc."''<br />
<br />
== Misc. Notes ==<br />
The<br />
<br />
== Homework ==<br />
<br />
=== Assignment 1 ===<br />
* All Exercises on Ch1, Simulating Discrete Random Variables with MATLAB (pp 51, 52, 53)<br />
* Type your solutions and hand in by midterm<br />
<br />
=== Assignment 2 ===<br />
* Summarize Chapters 0, and chapter 1 sec 0. <br />
* Type in your summary and hand in by May 14 2013<br />
<br />
=== Assignment 3 ===<br />
* Exercise section 5 of chapter 1: Analyzing n-tuples in some data bases<br />
* No need to do anything with entropy right now, just do the practical stuff<br />
<br />
=== Fun code to look at ===<br />
* experimental algorit being developed by Renato Fabbri for using basic word occurence statistics for text synthesis [http://labmacambira.git.sourceforge.net/git/gitweb.cgi?p=labmacambira/PLN;a=blob;f=ngramas.py;h=1fa6b86f5f315ffdbf487d5a1f43ecd3e11d6bb0;hb=HEAD] for his ongoing Introduction to Natual Language Processing course at [http://www.icmc.sc.usp.br ICMC-USP]<br />
<br />
== Keywords ==<br />
Portuguese: Teoria dos Padrões, Reconhecimento de Padrões, Visão Computacional, Inteligência Artificial, Formação de Padrões<br />
<br />
<br />
<br />
[[Category:IPRJ]] [[Category:Lab Macambira]]</div>V1z