Latest events

Human performance in the lab and in complex environments

Date: Tue, 9 Jul 2024
Location: AIML

Humans actively gather visual information to guide interaction with their environment. Human vision is very efficient and highlights how a small amount of data can be used to drive inferences that can be acted on. Our group investigates the basic mechanisms underlying active vision. We also work with industry to translate these results for outcomes relevant to human-AI interaction in complex environments. In this talk, Prof Ma-Wyatt provides an overview of her work in these areas and highlight opportunities for collaboration.

AIML Connect Fridays: Rising Sun Pictures

Alex Meddick, Thomas Rowntree, and Robert Beveridge from Rising Sun Pictures

Date: Fri, 12 Jul 2024
Location: AIML

Rising Sun Pictures (RSP) experts showcased how they are integrating machine learning workflows into special effects creation, ultimately empowering compositing artists with unprecedented creative control. This session was for anyone interested in the intersection of visual effects (VFX) and machine learning, providing insights into the cutting-edge techniques that are transforming the industry.

AIML Special Presentation: Dr. Sebastian Sequoiah-Grayson

Date: Fri, 12 Jul 2024
Location: AIML

Presentation by Dr. Sebastian Sequoiah-Grayson, a researcher with the University of New South Wales Sydney, on Formal Methods and Theoretical AI. The event delved into cutting-edge advancements and methodologies in AI research.

HDR Information Session

Date: Fri, 19 Jul 2024
Location: AIML

AIML hosted approximately 53 higher degree by research (HDR) students during our HDR Information Session on 19 July 2024.

AIML Research Seminar: Category Level 6D Object Pose Estimation and Tracking using Diffusion

Date: Tue, 23 Jul 2024
Location: AIML

In our daily lives, we constantly estimate the 6D pose of objects—whether it's picking up a coffee mug, catching a football on a Saturday afternoon, or avoiding a toy car rolling toward us. Even if we have never seen these particular objects before, our extensive knowledge of the world and the stereo vision of our eyes enable us to perform these tasks effortlessly. However, for a robot or computer with only a single image, this task is extremely challenging.

Department for Education visit

Yanyuan Qiao operates the AIML robot dog

Date: Thu, 8 Aug 2024
Location: AIML

AIML hosted over 100 secondary school students during the Education and School Tours at Lot Fourteen event hosted by the South Australian Department of Education.

AIML Research Seminar: Embracing Changes in Deep Learning: Continual Learning with Augmented and Modularised Memory (with Pre-trained Models)

Date: Tue, 20 Aug 2024
Location: AIML

Conventional DL approaches focus on the end results on fixed datasets/scenarios and fail to handle the dynamically raised novel requirements in the real world. Continual learning (CL) aims to train deep neural networks (DNNs) to efficiently accumulate knowledge on dynamically arriving data and task streams like humans. The main challenges include how to enable DNNs to learn on data and task streams with non-stationary distributions without catastrophic forgetting. To ensure DNNs effectively retain past knowledge while accommodating future tasks with a balance between stability and plasticity, we explore CL techniques from the viewpoint of augmenting and modularising the memorisation of DNNs. Given pre-trained models, do we need continual learning or how should we use continual learning? This talk delved into investigating how to continually perform adaptive learning with the pre-trained models and how to continually enhance pre-trained models.

AIML Special Presentation: Translating Running Gait Assessments to In-field Application Using Wearable Sensors

Date: Fri, 23 Aug 2024, 10:30 am - 11:15 am
Location: AIML

Dr Joel Fuller is a Sports Scientist and Physiotherapy researcher from Macquarie University. He has expertise in research areas related to biomechanics, wearable technology, performance enhancement and injury prevention. Joel presented findings from his most recent wearable technology research which used IMU systems to (1) identify fatigue onset in athletes during an intensive running training intervention and (2) identify and retrain runners at high risk of impact-related injuries. He described how his work is seeking to engage with machine learning and deep learning to enhance performance and injury prevention outcomes for athletes and explore potential avenues for research translation.

Australian Information Industry Association (AIIA) Awards Finalists Visit AIML

AIML Business and Development Manager, Matthew Cliff, presents to the AIIA Awards finalists

Date: Thu, 29 Aug 2024, 10:45 am - 11:45 am
Location: AIML

AIML welcomed the finalists of the (AIIA) Awards with a tour of our institute. These finalists represent a diverse range of innovators from across Australia, including individuals, groups, government, and private organisations. Our Business and Development Manager, Matthew Cliff, led the tour showcasing AIML’s research innovations and addressed many enthusiastic questions on specific use cases of AI adoption across various industries.

AIML Research Seminar: How Has AI/ML Accelerated Genomic Discovery?

Date: Tue, 3 Sep 2024, 10:30 am - 11:15 am
Location: AIML

Dr Denis Bauer is a government research scientist, adjunct professor at Macquarie University and an AWS Hero. Her unique approach of joining cloud-computing with deep biological domain knowledge translates research into impactful products that have been used for disease gene detection in Motor Neuron Disease and the COVID-19 vaccine development. She contributes to advisory committees and open-source software projects, as well as keynotes international IT and Medical conferences. She was recognized as Brilliant Women in Digital Health 2021 and Women in AI 2022. She has attracted more than $41M in funding to further life-science research and digital health.

��ģ��