### SISE 9128: Introduction to Machine Learning

#### Overview

Machine learning is an exciting new subject dealing with automatic recognition of patterns (e.g. automatic recognition of faces, postal codes on envelopes, speech recognition), prediction (e.g. predicting the stock market), datamining (e.g. finding good customers, fraudulent transactions), applications in bioinformatics (finding relevant genes, annotating the genome, processing DNA Microarray images), or internet-related problems (spam filtering, searching, sorting, network security). It is becoming a key area for technical advance and people skilled in this area are worldwide in high demand.Some companies using machine learning:

#### Formal Description

This unit introduces the fundamentals of machine learning, based on linear and kernel classifiers. The course requires mathematical and computer skills. It will cover linear algebra and numerical mathematics techniques, linear classification, regression, mathematical programming, the Perceptron, Online Learning, Regression methods, Kernels and Regularization.#### Presenter

Dr. Alexander J. SmolaRSISE, Australian National University

Canberra, ACT 0200

Phone : (+61) 2 6125-8652

Cellular: (+61) 410 457 686

Fax: (+61) 2 6125-8651

[email protected]

#### Dates of the Course

The course will be held on **October 8 - 19**, with daily lectures at
**8.15-10.00 am**. The first three days of each week are used for lectures,
the last two days for supplementary tutorial material. Completion of the
assignment sheets is optional, however I **strongly encourage students** to
**solve the problems on their own before the tutorials**, since this
information will be useful for the exam.

The assessment will be in the form of oral exams, probably one week after the end of the lectures.

#### Time and Effort Required

In accordance with the guidelines of RSISE this course is designed not to require more than 60 hours of time from the students (this unfortunately also limits the amount of knowledge, students are able to gain from the course). More specifically, the time needed is 20 hours for the attendance of the lectures, 20 hours of assignments (you should not need more than 5 hours per assignment sheet), and 20 hours of extra reading.#### Prerequisites

#### Contents

**Week 1:**Linear Algebra, Hilbert Spaces, Numerical Mathematics, Problems in Learning Theory, Statistics and Probability, Risk Functional, Common Distributions, Perceptron

Lectures 1, 2, 3, 4, 5, 6; Assignments 1 and 2.

**Week 2:**Regression, Squared Loss, Noise Models and Loss, Regularization, Bayesian Inference, Kernels, Kernel Perceptron, Kernel Regression

Lectures 7, 8, 9, 10, 11, 12; Assignments 3 and 4.