Log in

CPD156- A crash course on using machine learning methods effectively in practice

  • 22 Nov 2022
  • 9:00 AM - 5:00 PM (AEDT)
  • 12 Second Way 430 Active Learning Space, Room 430, 12 Second Way, Macquarie University
  • 49


Registration is closed

SSA NSW branch and School of Mathematical and Physical Sciences, Macquarie University are offering this in-person workshop presented by Prof. Benoit Liquet-Weiland and Dr Sarat Moka.

Deep learning can be viewed as a sub-discipline of machine learning and hence this first workshop provides an overview of key machine learning concepts and paradigms. The participant is introduced to supervised learning, unsupervised learning, and the general concept of iterative based optimization for learning. The concepts of training sets, test sets, and the like, together with principles of cross validation and model selection are introduced. Simple neural networks such as Logistic regression for binary classification and the related softmax regression model for multi-class problems will be exposed. This is where principles of deep learning such as cross entropy loss, decision boundaries, and simple cases of backpropagation are introduced. This course also presents a simple non-linear auto-encoder architecture. Aspects of model tuning are also discussed including feature engineering and hyper-parameter choice. The workshop includes machine learning demonstrations using R and Python software. This first workshop will equip attendees for the follow up workshop on “Mathematical Engineering of Deep Learning”.

Course Outline

  • -        An overview of the basic problems of machine learning (ML)
  • -        Supervised, unsupervised learning
  • -        Classification/regression techniques
  • -        A demonstration of basic classifiers. Performance measures such as accuracy, recall, and precision, F1-score.
  • -        Differences between ML approaches and statistics approaches to problem solving.
  • -        Train, Dev/Validate, Test/Production sets, K-fold cross validation.
  • -        Hyper-Parameters.
  • -        Bias-variance tradeoff.
  • -        Taste of unsupervised learning
  • -        K-means, image segmentation
  • -        PCA and SVD
  • -        Introduction to non-linear auto-encoder architecture

Course Timetable (including morning tea, lunchtime and afternoon tea breaks)

Below is the tentative schedule for the workshop, it will be adapted on the workshop day.

9:00 – 10:45

Session 1

10:45 – 11:15 (30 mins)

Moring tea break

11:15 – 12:45

Session 2

12:45– 13:45 (1 hour)

Lunch Break

13:45 – 15:15

Session 3

15:15 – 15:45 (30 mins)

Afternoon tea break

15:45 – 17:00

Session 4

Target Audience: From engineering, signal processing, statistics, physics, econometrics, operations research, quantitative management, pure mathematics, bioinformatics, applied machine learning, or even applied deep learning.

Learning Objectives

  • ·       Understand the principles of machine learning
  • ·       Understanding of the fundamental models, algorithms, and techniques of machine learning
  • ·       Understand supervised and unsupervised learning
  • ·       Apply different machine learning techniques on real data sets using software packages (R and Python)
  • ·       Build knowledge in machine learning for next workshop on deep learning models

Presenters Biography

Dr Liquet is a Professor of Mathematical and Computational Statistics at Macquarie University in the School of Mathematical and Physical Sciences. In addition, he is affiliated with the University of Queensland and to the Université de Pau et Pays de l'Adour (UPPA). He was previously affiliated with ACEMS (Centre of Excellence for Mathematical and Statistical Frontiers), Queensland University of Technology. Throughout his career, he has extensively worked in developing novel statistical models, mainly to provide novel tools to analyse clinical, health and biological data arising from epidemiological studies. Since 2011, he moved to the field of computational biology and generalised some of these methods so that they scale to high throughput ("omic") data. He taught an advanced course on the mathematical engineering of Deep Learning at the Australian Mathematical Sciences Institute (AMSI) summer school in 2021. A book draft of his new co-authored book on concepts of "Deep Learning" is available at . Benoit Liquet works on Applied Statistics, as well as on the development of R packages and on industrial applications (such as Machine Learning).


Dr Sarat Moka is a Research Fellow in the School of Mathematical and Physical Sciences at Macquarie University. He was previously an ACEMS (ARC Centre for Excellence for Mathematical & Statistical Frontiers) Postdoc at The University of Queensland. He has obtained a PhD in Applied Probability from the Tata Institute of Fundamental Research, Mumbai, and Master of Engineering from the Indian Institute of Science, Bengaluru. He has been working on problems in Statistics, Applied Probability, and Deep Learning. In addition, he has worked on modelling cancer data and on the Safe Blues project ( He has been teaching advanced courses in Statistics and Deep Learning, including a Deep Learning course at the Australian Mathematical Sciences Institute (AMSI) summer school in 2021, and is currently co-writing a book on "The Mathematical Engineering of Deep Learning" (

Powered by Wild Apricot Membership Software