42820 Machine Learning Foundations

Warning: The information on this page is indicative. The subject outline for a particular session, location and mode of offering is the authoritative source of all information about the subject for that offering. Required texts, recommended texts and references in particular are likely to change. Students will be provided with a subject outline once they enrol in the subject.

Subject handbook information prior to 2024 is available in the Archives.

Description

This microcredential introduces the essential elements of machine learning - a technique that enables a machine to learn from data to automatically derive or enhance its strategy to perform its tasks. Taking a research-inspired approach, the microcredential guides learners to apply state-of-the-art algorithms to their professional practice with a focus on practical applications. The microcredential presents learners with core concepts in machine learning as well as a generic framework. Basic learning models, including decision trees and linear families, demonstrate the theory of machine learning. These models are also widely applied in real-world applications.

Subject learning objectives (SLOs)

Course intended learning outcomes (CILOs)

This subject also contributes specifically to the development of the following Course Intended Learning Outcomes (CILOs):

• Technically Proficient: FEIT graduates apply theoretical, conceptual, software and physical tools and advanced discipline knowledge to research, evaluate and predict future performance of systems characterised by complexity. (D.1)

Teaching and learning strategies

The study will be both theoretical and practical. As for the theory, the microcredential provides a systematic view of the whole lifecycle of a data model, from the design motivation to the dynamics in the learning process, and the evaluation and how reliable the evaluation results are. On the practical side, learners will be led to translate math notions into data structures and programs in a digital computer, which allows them to ‘open the hood’ of the data models and get hands-on experience to examine piece-by-piece how the models perform learning. Microcredential presentation includes weekly synchronous one-hour online workshops facilitated by an expert UTS academic(s) supporting self-study and online (LMS) learning activities. Regular formative quizzes throughout the semester will allow learners to gauge their progress.

Content (topics)

1. Machine Learning Problem

   1. Overview

   2. Essential Components in a Machine Learning Problem

   3. Example Problem

   4. Formal Definition and Framework

   5. More practical examples

2. Linear Models

   1. Definition and Overview

   2. Perceptron

   3. Training a Perceptron

   4. Linear Regressor, Definition and Training

   5. Implementation Tutorial

3. Decision Trees

   1. Decision Trees Motivated from an Information Theoretical Viewpoint

   2. Measuring Information with Entropy

   3. How Decision Trees Work

   4. Build a Decision Tree

   5. Implementation Tutorial

4. Errors, Evaluation and Noises

   1. Loss in Learning

   2. Pointwise Error

   3. Generalisation Error

   4. Noises

   5. Summary

Assessment

Assessment task 1: Algorithm Implementation and Report

Minimum requirements

In order to pass the microcredential, a learner must achieve an overall mark of 50% or more.