COSC401-14S1 (C) Semester One 2014

Machine Learning

15 points

Details:
Start Date: Monday, 24 February 2014
End Date: Sunday, 29 June 2014
Withdrawal Dates
Last Day to withdraw from this course:
  • Without financial penalty (full fee refund): Friday, 7 March 2014
  • Without academic penalty (including no fee refund): Friday, 23 May 2014

Description

A study of computational processes that underlie learning in both humans and machines. Topics will include inductive, analytical and case-based learning, genetic algorithms and neural networks.

Machine Learning is the study of how computer programs can improve their performance automatically through experience, or "learn from experience". At the end of this course you will have a broad overview of this rapidly growing area. You will also be able to critically assess the potential of various Machine Learning paradigms and techniques.

Topics
-------------

The course covers major paradigms of learning including supervised, unsupervised, and reinforcement learning. The course discusses the following techniques:

- Linear models
- Kernels and Support Vector Machines
- Neural networks
- Probabilistic models (parametric and non-parametric methods)
- Graphical models (Bayesian networks and Hidden Markov model)
- Evolutionary computation and meta-heuristic approaches
- Lazy learning
- Ensemble learning

The course shows how the above-mentioned techniques are used in practice to achieve tasks such as:

- System identification, function approximation, and regression
- Decision making, prediction and classification
- Clustering and outlier detection
- Learning new strategies

Prerequisites

1) COSC367 2) Subject to approval of the Head of Department

Course Coordinator

Kourosh Neshatian

Assessment

Assessment Due Date Percentage 
Assignment 1 25%
Assignment 2 25%
Final Exam 50%

Textbooks / Resources

Recommended Reading

Bishop, Christopher M; Pattern recognition and machine learning ; Springer, 2006.

Witten, I. H. , Frank, Eibe., Hall, Mark A; Data mining : practical machine learning tools and techniques ; 3rd ed; Morgan Kaufmann, 2011.

Additional Course Outline Information

Grade moderation

The Computer Science department's grading policy states that in order to pass a course you must meet two requirements:
1. You must achieve an average grade of at least 50% over all assessment items.
2. You must achieve an average mark of at least 45% on invigilated assessment items.
If you satisfy both these criteria, your grade will be determined by the following University- wide scale for converting marks to grades: an average mark of 50% is sufficient for a C- grade, an average mark of 55% earns a C grade, 60% earns a B- grade and so forth. However if you do not satisfy both the passing criteria you will be given either a D or E grade depending on marks. Marks are sometimes scaled to achieve consistency between courses from year to year.

Aegrotats
If factors beyond your control (such as illness or family bereavement) prevent you from completing some item of course work (including laboratory sessions), or prevent you from giving your best, then you may be eligible for aegrotat, impaired performance consideration or an extension on the assessment. Details of these may be found in the University Calendar. Supporting evidence, such as a medical certificate, is normally required. If in doubt, talk to your lecturer.

Indicative Fees

Domestic fee $881.00

* All fees are inclusive of NZ GST or any equivalent overseas tax, and do not include any programme level discount or additional course-related expenses.

For further information see Computer Science and Software Engineering .

All COSC401 Occurrences

  • COSC401-14S1 (C) Semester One 2014