Join the SSA ACT Branch for a practical, hands-on workshop, Deep Learning and Computer Vision in R: A Practical Introduction, presented by Dr Patrick (Weihao) Li from the Australian National University (ANU).
EARLY BIRD REGISTRATION NOW OPEN!
Register early to secure your place and take advantage of the Early Bird rate. Limited places available.
Date : Tuesday 17th November & Wednesday 18th November 2026
Time: 1.30pm to 5.00pm on both days
Format: Online via Zoom.
Zoom access details will be provided in your registration confirmation.
About the Workshop
Deep learning has transformed how we extract insights from images, powering applications across diverse fields such as medical imaging, precision agriculture, autonomous systems, and industrial inspection. While these techniques are increasingly important in modern research, many applied statisticians are unfamiliar with the key concepts and tools behind deep learning and computer vision.
Presenter's Bio - Dr Patrick (Weihao) Li, ANU
Dr Patrick (Weihao) Li is a Postdoctoral Research Fellow at the Australian National University, working on the Analytics for the Australian Grains Industry (AAGI) project. He holds a PhD in Statistics from Monash University. His research spans machine learning, data visualization, statistical modelling, and computer vision, with a focus on developing computational methods for analysing and interpreting complex data. His current research applies these methods to agricultural, biological, and public health applications. Within the AAGI project, he investigates the interpretation, robustness, and uncertainty of Vision Transformer-based models for automated canola blackleg severity quantification, and contributes to the development of new computational frameworks for fitting complex linear mixed models. He has also contributed to computer vision projects in IVF embryo assessment and video-based food safety monitoring using object detection and vision-language models
Key Learnings:
This hands-on workshop introduces the fundamentals of deep learning and its applications in computer vision, with a focus on accessibility for R users. We will begin with a high-level overview of deep learning and neural networks, building intuition for the key components of modern deep learning models, including layers, activation functions, model training, and optimisation. The workshop will then introduce core computer vision techniques, including convolutional neural networks (CNNs) for image analysis and more recent approaches such as Vision Transformers (ViTs), which have become increasingly important in modern computer vision applications. Through practical examples, participants will explore how deep learning models can be applied to tasks such as:
- Image classification (e.g. assigning images to different categories)
- Object detection (e.g. identifying and locating objects within images)
- Image segmentation (e.g. identifying and delineating objects or regions at the pixel level)
All workshop activities will be conducted in R, with the reticulate package used to access Python-based deep learning tools. Participants will set up a local Python environment using conda and install the required deep learning libraries before the workshop. Setup scripts and a test script will be provided in advance to help participants verify that their environment is ready.
Participant Requirements
Participants should:
- Have a working R and RStudio installation, and complete the required environment setup before the workshop (detailed setup instructions and a test script will be provided in advance)
- Be comfortable with basic R tasks (e.g. loading data, using functions, navigating RStudio)
- Have familiarity with basic statistical concepts (e.g. regression, classification, and model evaluation)
- Be connected via Zoom for workshop participation
Desirable
- No prior experience with deep learning, computer vision, or Python is required
- Some familiarity with matrices, linear algebra, or optimization concepts may help with understanding key ideas, but is not necessary
- Experience with statistical modelling or data analysis workflows is beneficial
Cancellation Policy:
Cancellations received prior to two weeks before the event will be refunded, minus the Stripe processing fee (1.75% + $0.30 per transaction) and an SSA administration fee of $20.
From then on, no part of the registration fee will be refunded. However, registrations are transferable within the same organisation. Please advise any changes to events@statsoc.org.au.
@StatSocAus
