1

CVG-UPMC

OM

PU

TE

R V

ISIO

N

Neural Networks and Pattern RecognitionP. Campoy

?

by

?Machine Learning

andNeural Networks

Pascual Campoypascual.campoy@upm.es

Computer Vision GroupUniversidad Politécnica Madrid

2

CVG-UPM

CO

MP

UT

ER

VIS

ION

Neural Networks and Pattern RecognitionP. Campoy

table of contents

What is it about?

Objectives

Topics

Scheduling

Evaluation

Methodology

Learning material

Class-room exercises

3

CVG-UPMC

OM

PU

TE

R V

ISIO

N

Neural Networks and Pattern RecognitionP. Campoy

machine intelligencemachine learning

data mining

pattern recognition

artificial neural networks

dimensionality reduction

intelligence

What is it about?

4

CVG-UPM

CO

MP

UT

ER

VIS

ION

Neural Networks and Pattern RecognitionP. Campoy

Objectives:

Be able to explain following terms andrelate them to real-word problems:- learning, pattern recognition, classification,

dimensionality reduction, supervised learning,unsupervised learning

Ability to apply classical PR techniques- PCA, Bayesian Decision & K-means

Ability to apply supervised ANN:- MLP to PR

Ability to apply unsupervised ANN:- SOM to PR

5

CVG-UPMC

OM

PU

TE

R V

ISIO

N

Neural Networks and Pattern RecognitionP. Campoy

Topics:

1. Intelligence & learning

2. Feature processing

3. Classical classifiers

4. Machine Learning

1st. Part(exam and work)

2nd. Part(exam and work)

5. Bio-inspiration

6. Supervised ANN: Multilayer Perceptron

7. Non supervised ANN: Self-organized Maps

6

CVG-UPM

CO

MP

UT

ER

VIS

ION

Neural Networks and Pattern RecognitionP. Campoy

Schedule …

Topic Subject Week/day

0 Guide to the subject 15-S

1 Intelligence & Learning 22-S

2 Feature processing 29-S, 6-O

3 Classical Classifiers 13-O

4 Machine learning 20-O

5 Bio-inspiration 27-O

6 a Supervised Neural Networks: MLP 3-N

1-2-3-4 Presentation Parctical Work #1 10-N

1-2-3-4 1st Exam 17-N

6 b Supervised Neural Networks: MLP 24-N

7 Unsupervised Neural Networks: SOM 1-D

4-5-6-7 Presentation Parctical Work #2 15-D

2nd. Exam 31-J

Schedule 2010-2011 for "Pattern Recognition & Neural Networks"

7

CVG-UPMC

OM

PU

TE

R V

ISIO

N

Neural Networks and Pattern RecognitionP. Campoy

… schedule

3 ECTS x 25 hours/ECTS = 75 hours

- Classroom 28 hours:14 weeks x 2 hours/week

- Outside the classroom 47 hours:47 hours/14 weeks = 3,5 hours/week

8

CVG-UPM

CO

MP

UT

ER

VIS

ION

Neural Networks and Pattern RecognitionP. Campoy

Evaluation

Continuous evaluation- Class-room exercises ______

- Two practical works _______

- Two exams ______________

145

Momentary evaluation- Practical works (compulsory)__

- Oral exam ______________1,58,5

9

CVG-UPMC

OM

PU

TE

R V

ISIO

N

Neural Networks and Pattern RecognitionP. Campoy

Methodology …

Roger Schank interviewedby Eduardo Punset

Practice:

http://scaleup.ncsu.edu/

Collaborative: SCALE-UP

classroom at MIT

10

CVG-UPM

CO

MP

UT

ER

VIS

ION

Neural Networks and Pattern RecognitionP. Campoy

… methodology

In the collaborative classroom:- Lecture- Collaborative working on the computer- Tutorial- Presentation of practical works

Out of the classroom:- Individual study (bofore-after)- Two Practical Works

In the informatics classroom:- Two individual exams

11

CVG-UPMC

OM

PU

TE

R V

ISIO

N

Neural Networks and Pattern RecognitionP. Campoy

Learning material …

Aulaweb:

invited student “pr53000038”, password “learning”- This guide: “0_MLaNN_guide.pdf”- Slides for every topic, including classroom exercices- Two practical works- Dataset for exercises and pracical works, including exercise

form “exercises_template.doc”

12

CVG-UPM

CO

MP

UT

ER

VIS

ION

Neural Networks and Pattern RecognitionP. Campoy

… learning material

"Pattern Classification"Duda-R, Hart-P, Stork-DWiley-Interscience , 2004

“Pattern recognition & Machine Learning”Christopher M. Bishop

Springer, 2006

Books:

13

CVG-UPMC

OM

PU

TE

R V

ISIO

N

Neural Networks and Pattern RecognitionP. Campoy

Further reading …

Christof Koch Rodolfo Llinás V.S. Ramachandran

biological inspiration

14

CVG-UPM

CO

MP

UT

ER

VIS

ION

Neural Networks and Pattern RecognitionP. Campoy

… further reading

Jeff Hawkins David Fogel

making things to work

15

CVG-UPMC

OM

PU

TE

R V

ISIO

N

Neural Networks and Pattern RecognitionP. Campoy

Class-room exercices …

1. Create a word document from the template“exercises_template.doc” (downloaded fromAulaweb/contenidos/problemas) with the name: eX_YY_AAAAA_BBBBB_CCCCC.doc

where X is the chapter number

YY is the exercise number within the chapter

AAAAA, BBBBB and CCCCC are the students ID numbers

2. Save this document in your PC at

“Documentos compartidos/entregar”

16

CVG-UPM

CO

MP

UT

ER

VIS

ION

Neural Networks and Pattern RecognitionP. Campoy

… class-room exercices3. Fulfill the heading:

4. Write in the document the required solution that includes theexplanation, the Matlab code, the obtained graphics and results, andthe comments and conclusions

5. The document has to be closed in order to allow to be collected

17

CVG-UPMC

OM

PU

TE

R V

ISIO

N

Neural Networks and Pattern RecognitionP. Campoy

Example 0.1 change Matlab working directory to Documentos_ compartidos/entregar download “datos_D2_C3_S1” from Aulaweb into this directory >> load datos_D2_C3_S1

p.valor 2x1000

p.clase 1x1000

p.salida 1x1000

>> plot(p.valor(1,:),p.valor(2,:),’b.’); hold on;

18

CVG-UPM

CO

MP

UT

ER

VIS

ION

Neural Networks and Pattern RecognitionP. Campoy

Exercise 0.1

>> load datos_D2_C3_S1.mat Print p.valor using a diferent color/prompt for each clase

determined in p.clase

20

CVG-UPMC

OM

PU

TE

R V

ISIO

N

Neural Networks and Pattern RecognitionP. Campoy

What is PR by learning?

?