Latest events
Search events
Enter a keyword to search events within the date range above.
AI on the Ground Seminar: What if you could start over with what you know now?
- Date: Fri, 27 Jun 2025, 10:30 am - 11:30 am
- Location: AIML
This session explores the transition from academic AI prototypes to operational systems within clinical environments. Drawing from experiences at SickKids and now Seattle Children’s, this strategic and reflective talk will share key insights from previous successes and failures, with the goal of fostering dialogue and community learning around applied clinical AI.
[Read more about AI on the Ground Seminar: What if you could start over with what you know now?]
AIML Connect Fridays: Bombshell – The Hedy Lamarr Story
- Date: Fri, 20 Jun 2025, 4:00 pm - 5:30 pm
- Location: AIML
Join us for AIML Connect Fridays to watch Bombshell – The Hedy Lamarr Story. In this documentary, discover the untold story of Hedy Lamarr: Hollywood star, scientific visionary, and the woman behind one of the most valuable technological breakthroughs of the 20th century.
[Read more about AIML Connect Fridays: Bombshell – The Hedy Lamarr Story]
AIML Research Seminar: Adversarial attacks against machine learning models for satellite imagery
- Date: Tue, 3 Jun 2025, 10:30 am - 11:15 am
- Location: AIML
Satellites utilise a wide range of sensing modalities to collect data for applications such as earth observation, navigation and disaster management. Hyperspectral imagery is one such modality that captures a detailed spectral response of scenes across the electromagnetic spectrum. This type of imagery, however, generates vast amounts of data which requires processing to extract meaningful insights. To permit real-time decision making, edge computing – performed directly onboard a satellite – is used to process data before transmission to ensure only essential data is downlinked, ensuring fast response times. This is critical for time-sensitive applications including disaster detection and military surveillance. Deep neural networks (DNNs) are increasingly being used to automate this processing onboard satellites due to their ability to detect objects and anomalies faster and more accurately than traditional methods. However, DNNs are susceptible to adversarial attack. These attacks involve placing engineered objects into the scene of an image that cause deep neural networks to produce incorrect outputs. This research explores the vulnerability of DNNs to adversarial attack in satellite imagery and investigates methods to enhance the reliability of DNNs in the presence of such threats.
![RSS News Feed](/global/images/rss.gif" "RSS News Feed"){kind=small}