1. 2 machine learning يادگيري ماشين lecturer: a. rabiee [email protected]...

28
1

Upload: martin-hicks

Post on 21-Jan-2016

216 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

1

Page 2: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

2

Machine Learning

يادگيري ماشين

Lecturer: A. Rabiee [email protected]

Page 3: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

منابع و مراجع

Main Reference:- Mitchell, T. M. (1997). Machine learning. WCB.Other References:- Haykin, S. S. (2009). Neural networks and learning machines (Vol. 3). Upper Saddle River:

Pearson Education.- Mitchell, T. M. (1999). Machine learning and data mining. Communications of the

ACM, 42(11), 30-36.- Anderson, J. R. (1986). Machine learning: An artificial intelligence approach(Vol. 2). R. S.

Michalski, J. G. Carbonell, & T. M. Mitchell (Eds.). Morgan Kaufmann.- Mitchell, M. (1998). An introduction to genetic algorithms. MIT press.- Witten, I. H., & Frank, E. (2011). Data Mining: Practical machine learning tools and

techniques. Morgan Kaufmann.- Hagan, M. T., Demuth, H. B., & Beale, M. H. (1996). Neural network design(pp. 2-14).

Boston: Pws Pub..- Kecman, V. (2001). Learning and soft computing: support vector machines, neural

networks, and fuzzy logic models. MIT press.- - ….

3

Page 4: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

Course Outline

• Chapter 1: Introduction• Chapter 3: Decision tree learning• Chapter 4: Artificial Neural

Networks• Chapter 9: Genetic Algorithms• Chapter 13: Reinforcement

Learning

Page 5: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

ارزشيابي درس

Final Exam: 50Mini Projects (2 to 4): 20Final Project + Presentation: 30Paper (optional): +15

4

Page 6: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

Chapter 1:

Introduction to Machine Learning

Page 7: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

Table of Contents

• Definition & Examples• Applications• Why ML?• ML Problems

Page 8: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

Definition (Mitchell 1997)

• Machine Learning– Learn from past experiences– Improve the performances of

intelligent programs• Definition

– A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at the tasks improves with the experiences

Page 9: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

Examples

• Text Classification (or spam classification)– Task T

• Assigning texts to a set of predefined categories

– Performance measure P• Precision of each category

– Training experiences E (Dataset)• A dataset of texts with their corresponding

categories

• How about Disease Diagnosis?• How about Chess Playing?

Page 10: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

Two phases

• Two phases of a learning process:– Train– Test

Page 11: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

Example: Classification of texts based on content

Text classifierNew text file class

Classified text files

Text file 1 trade

Text file 2 ship

… …

Training

Phase 1: train

Phase 2: test

Page 12: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

Example:Heart disease diagnosis

Disease classifierNew patient’s

dataPresence or

absence

Database of medical records

Patient 1’s data Absence

Patient 2’s data Presence

… …

Training

Page 13: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

Example: Chess Playing

Strategy of Searching and

Evaluating

New matrix representing the current

board

Best move

Games played:

Game 1’s move list Win

Game 2’s move list Lose

… …

Training

Page 14: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

Machine Learning Problems

Clustering: Grouping similar instancesDimension Reduction: Image CompressionRegression: Tuning the angle of a robot arm

Page 15: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

Application: Image Categorization (two phases)

Training LabelsTraining

Images

Classifier Training

Training

Image Features

Trained Classifier

Image Features

Testing

Test Image

Trained Classifier Outdoor

Prediction

Page 16: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

Feature Extraction

Training LabelsTraining

Images

Classifier Training

Training

Image Features

Trained Classifier

Page 17: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

Example: Boundary Detection

• Is this a boundary?

Page 18: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

Training Algorithm

Training LabelsTraining

Images

Classifier Training

Training

Image Features

Trained Classifier

The main aim of this course

Page 19: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

Classifier TrainingExample: A 2-class classifier

• Given some set of features with corresponding labels, learn a function to predict the labels from the features

• Example: Credit scoring

Discriminant (model): IF income > θ1 AND savings > θ2 THEN

low-risk ELSE high-risk

Page 20: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

Different Learning Algorithms

• Decision Tree Learning• Neural networks • Naïve Bayes• Genetic Algorithm• K-nearest neighbor (clustering)• Reinforcement Learning• Support Vector Machine (SVM)• …

Page 21: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

Note

The decision to use machine learning is more important than the choice of a particular learning method.

Page 22: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

Why Machine Learning Is Possible?

• Mass Storage– More data available

• Higher Performance of Computer– Larger memory in handling the data– Greater computational power for

calculating and even online learning

Page 23: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

Advantages

• Alleviate Knowledge Acquisition Bottleneck– Does not require knowledge engineers– Scalable in constructing knowledge

base

• Adaptive– Adaptive to the changing conditions– Easy in migrating to new domains

Page 24: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

Success of Machine Learning

• Almost All the Learning Algorithms– Text classification (Dumais et al. 1998)– Gene or protein classification

optionally with feature engineering (Bhaskar et al. 2006)

• Reinforcement Learning– Backgammon (Tesauro 1995)

• Learning of Sequence Labeling– Speech recognition (Lee 1989)– Part-of-speech tagging (Church 1988)

Page 25: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

Datasets

• UCI Repository: http://www.ics.uci.edu/~mlearn/MLRepository.html

• UCI KDD Archive: http://kdd.ics.uci.edu/summary.data.application.html

• Statlib: http://lib.stat.cmu.edu/

• Delve: http://www.cs.utoronto.ca/~delve/

• US government free data: data.gov

• US government free data (California): data.ca.gov

• …. for other states and the UK data.gov.uk, as well• Stock market softwares• Weather forecasting websites• Reuters: data set for text classification• ….

Page 26: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

What I will Talk about

• Machine Learning Methods– Simple methods– Effective methods (state of the art)

• Method Details– Ideas – Assumptions– Intuitive interpretations

Page 27: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

What I won’t Talk about

• Machine Learning Methods– Classical, but complex and not effective methods

(e.g., complex neural networks)– Methods not widely used

• Method Details– Theoretical justification– Theorem proving

Page 28: 1. 2 Machine Learning يادگيري ماشين Lecturer: A. Rabiee azrabiee@gmail.com Rabiee.iauda.ac.ir

What You will Learn

• Machine Learning Basics– Methods– Data– Assumptions– Ideas

• Others– Problem solving techniques– Extensive knowledge of modern techniques