Designed for professionals with some familiarity with machine learning (ML), this microcredential will provide a deeper understanding of statistical learning theory and empirical risk minimisation, allowing participants to improve their ML models and algorithms. The microcredential covers both theoretical considerations and hands-on, under-the-hood coding exercises.

About this microcredential

This microcredential introduces some advanced machine learning data models, algorithms and theoretical results. It focuses on key considerations, such as building data models with neural networks, deep neural network (DNN) architecture and generalised linear models and kernel methods and learning data models covering gradient-based algorithms and optimisation, backpropagation and constrained optimisation practice.

It also considers improving model reliability using DNN structures to enable learning stability and regularisation techniques, as well as exploring why learned models can be trusted through the risk theory of learning-based models, looking at bias, variance, training and test evaluation.

Key benefits of this microcredential

Upgrade your machine learning models and projects – develop the knowledge and skills to build and understand more reliable models
Gain an in-depth coverage of the theoretical models and considerations underpinning machine learning and some practical coding exercises to demonstrate them
Complete as a self-contained course, or as a potential pathway to future postgraduate study.

This microcredential aligns with the two-credit point subject, Advanced Machine Learning (42894) in the Graduate Certificate in Professional Practice (C11298), Graduate Diploma of Professional Practice (C06136), Master of Professional Practice (C04404), Graduate Certificate in Technology (C11301), Graduate Diploma in Technology (C06137) and Master of Technology (C04406).

This microcredential may qualify for recognition of prior learning at this and other institutions.

Who should do this microcredential?

This microcredential is suitable for professionals from a wide range of sectors and backgrounds, who have completed the Machine Learning Foundations microcredential, or otherwise have some professional experience in the field and are comfortable working in Python.

UTS microcredentials are developed for professionals with a capacity to undertake postgraduate tertiary education.

Price

Full price: $1,595.00 (GST-free)*

*Price subject to change. Please check price at time of purchase.

Enrolment conditions

Course purchase is subject to UTS Open Terms and Conditions.

COVID-19 response

UTS complies with latest Government health advice. Delivery of all courses complies with the UTS response to COVID-19.

Additional course information

Course outline

During this course you will meet and work with a dedicated course facilitator who will support your learning and engagement with teaching resources designed by the lead academic and team of experts from the Faculty of Engineering and IT.

The course is structured into five modules. Each module comprises self-study materials and facilitated online sessions. The five modules and key topics covered are:

Module 1 - Neural networks

This module covers the construction, computation and training of neural networks. You will develop hands-on experience of building neural network models and knowledge of the state-of-the-art NN models in different application areas.

Module 2 - Machine learning theory

This module covers a discussion of learning from experience and goes into depth on Hoeffding’s inequality to consider the bounds on reliability.

Module 3 - Convolutional neural networks

This module covers the motivation behind convolutional neural networks and focuses on the computation and backpropagation of a convolutional layer.

Module 4 - Transformer families

This module introduces how self-correlation can be useful in a learning model and how to represent the correlation and implement the model as a block of neural networks. Participants will get hands-on experience in building a family of neural network from scratch and applying a transformer model to a practical data set.

Module 5 - Generative models

This module introduces generative adversarial networks (GANs), featuring a definition of the GAN model, the core training steps of GANs and a detailed walkthrough of implementing a GAN and evaluating the results.

Course delivery

This course includes weekly, live, one-hour online tutorials and one-hour weekly Q&A sessions facilitated by an expert UTS academic, supporting self-study and online learning activities.

Both theoretical and practical learning are covered. The course provides a systematic view of the whole life-cycle 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, participants will translate mathematical 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.

Regular formative quizzes throughout the microcredential will allow learners to gauge their progress.

Course learning objectives

Upon successful completion of this course you will be able to design machine learning algorithms with practical implementation for professional contexts.

Assessment

The graded assessment task comprises an individually written assessment on implementing one of the advanced machine learning algorithms, i.e., building a data model and adapting the model to observed data - according to the machine learning framework. The model will be tested against data and assessed using the evaluation criteria introduced in the course. The implementation process and evaluation are to be summarised in a report.

Length: 2,000 words

Requirements

Mandatory

To complete this online course, you will need a personal computer with reliable internet access, web conferencing capability and an operating system with a web browser compatible with the Canvas LMS. You will need to be able to run a currently-supported version of Python.

$1,595.00

START DATE	02 August
MODE	Online
DURATION	10 wks
COMMITMENT	Avg 5 hrs p/w

View all sessions

Lead Academic

Tianqing Zhu

Tianqing is an experienced lecturer in cybersecurity, with an extensive background in teaching and research in privacy preserving, cybersecurity and data analytics.

Tianqing’s research interests include designing novel privacy preserving models, developing efficient algorithms and performing in-depth analytics on a wide spectrum of very large, real-world data sets.

More Less