Introductory Applied Machine Learning
Course Homepage

Lecturers: Victor Lavrenko and Nigel Goddard
TA: Sean Moran

This page will grow as the course develops.

The goal of this course is to introduce students to basic algorithms for learning from examples, focusing on classification and clustering problems. This is a level 9 course intended for MSc students and 3rd year undergraduates.

For an overview of the planned course topics, see the Course Catalog entry and the 2011 introductory handout.

Lectures

14:10-15:00 Mondays and Thursdays in Appelton Tower, Lecture Theatre 1 (LT1).

Resources

Books. The course textbook is Data Mining: Practical Machine Learning Tools and Techniques (Second Edition, 2005) by Ian H. Witten and Eibe Frank.
Other good books:
- Pattern Recognition and Machine Learning by C. Bishop
- Elements of Statistical Learning by Hastie, Tibshirani and Friedman
- Bayesian Reasoning and Machine Learning by D. Barber
- Machine Learning by T. Mitchell
- Reinforcement Learning by R. Sutton and A. Barto
Past years' exam papers are available from 2009 and 2010.
The lecture notes from the old LfD course are useful, although they contain more mathematical detail than we are expecting for IAML.
A Few Useful Things to Know about Machine Learning by P. Domingos

This page is maintained by Victor Lavrenko and Nigel Goddard.

Discussion Forum

There is a discussion forum for this course. It contains previous year's questions and answers, but the topic list indicates clearly with ####### where the boundary is. This forum is monitored by both lectures and the TA, so if you ask questions here, you are likely to get a much faster response than if you email the lecturers individually. (However, if you have issues that should be kept confidential, then of course please do email the course lecturers.)

Assignments

There will be four equally-weighted assignments together worth 25% of the mark for the course. These will be released early in weeks 3, 5, 7 and 9, and will be due on Fridays at 4 p.m. in weeks 4, 6, 8 and 10. You are required to submit both an electronic copy and a manual copy to the ITO by the deadlines. The deadlines are strictly enforced.

Assignment #1

The question sheet a112_1.pdf is available. It is due at at 1600 on Fri 12 Oct 2012 by manual submission to ITO and electronic submission (please see question sheet for detailed submission instructions). The data files are here: train_20news_partA.arff, train_20news_partB.arff
Marks will be returned by 1600 on Fri 2 Nov 2012.

Assignment #2

The question sheet a112_2.pdf is available. It is due at at 1600 on Fri 26 Oct 2012 by manual submission to ITO and electronic submission (please see question sheet for detailed submission instructions). The data files are here: train_auto_partA.arff, train_auto_partA_base.arff, train_auto_partB_numeric.arff, train_auto_partB_full.arff, train_auto_partC.arff, valid_auto_partC.arff, test_auto_partC.arff
Marks will be returned by 1600 on Fri 16 Nov 2012.

Assignment #3

The question sheet a112_3.pdf is available. It is due at at 1600 on Fri 9 Nov 2012 by manual submission to ITO and electronic submission (please see question sheet for detailed submission instructions). The data files are here: train_images_partA.arff, valid_images_partA.arff, train_images_partB.arff, valid_images_partB.arff, test_images_partB.arff. The website where you can view the images from the validation dataset is here.
Marks will be returned by 1600 on Fri 30 Nov 2012.

Assignment #4

The question sheet a112_4.pdf is available. It is due at at 1600 on Fri 23 Nov 2012 by manual submission to ITO and electronic submission (please see question sheet for detailed submission instructions). The data files are here: cluster_means.txt, train_20news_partA.arff, train_mnist_dd01_partB.arff, train_mnist_dd02_partB.arff, train_mnist_binary_partC.arff, train_mnist_binary_pairConj_partC.arff.

Please read the Informatics policy on late submissions and plagiarism.

Tutorials

Tutorials will be in weeks 3, 5, 7 and 9. [Groups, times and rooms]

Lab Classes

Labs will be in weeks 3,5,7 and 9. [Groups, times and rooms]

Help with Maths

5pm Wednesday in AT3.03 in weeks 3,5,7,9. This is not a lecture, nor a tutorial. Please come with specific questions.

Week-by-Week listing

(This list is subject to change.)

Week 1

Lectures: Introduction [slides], [handout], mathematical preliminaries [slides], [handout], Thinking about Data [slides]
Readings: Textbook chapters 1, 2, 7.1, 7.2
Tutorials No tutorials in week 1 (nor week 2)
Mathematical preliminaries These Supplementary Mathematics notes are from the old Learning from Data course. They are more difficult than what we will need for IAML, but if you are happy with them you should have no problem with the IAML maths level.

Week 2

Lectures: Basic Probability and Estimation [slides],[handout] Naive Bayes Classification [slides]
Tutorials: No tutorials in week 2

Week 3

Lectures: Naive Bayes Classification [slides], Decision trees [slides]
Tutorial 1: Naive Bayes and data representation [solutions]
Lab 1: Naive Bayes classification

Week 4

Lectures: Generalization, overfitting and evaluation [slides]
Tutorials: No tutorials in week 4

Week 5

Lectures: Nearest neighbor method [slides], Linear regression [slides] [handout]
Tutorial 2: Decision Trees and kNN [solutions]
Lab 2: Attribute selection and Regression

Week 6

Lectures: logistic regresssion [1up],[4up], perceptrons [1up],[4up],
optimisation [1up],[4up],

Week 7

Lectures:Regularization [1up],[4up], Support vector machines part I [1up] [4up], Support vector machines Part II [1up] [4up]
Readings: SVM handout
Tutorials: Logistic regression [solutions]
Lab 3: Logistic regression, SVM, Feature Selection

Week 8

Lectures: K-means clustering [slides], Mixture models and the EM algorithm [slides]

Week 9

Lectures: Dimensionality reduction [slides]
Additional demo: Eigenfaces (not examinable)
Tutorials: SVMs, Clustering [solutions]
Lab 4: PCA, Clustering, Evaluation

Week 10

Lectures: Hierarchical clustering [slides]

Home : Teaching : Courses

Introductory Applied Machine Learning Course Homepage