Latest events
Search events
Enter a keyword to search events within the date range above.
AIML Special Presentation: Learning Spatial context-aware Global Visual Feature Representation for Instance Image Retrieval
- Date: Fri, 21 Jun 2024
- Location: AIML
In instance image retrieval, considering local spatial information within an image has proven effective to boost retrieval performance. It will be highly valuable to make ordinary global image representations spatial-context-aware because global representation based image retrieval is appealing thanks to its algorithmic simplicity, low memory cost, and being friendly to sophisticated data structures. This talk describes a novel feature learning framework proposed for instance image retrieval, which embeds local spatial context information into the learned global feature representations.
AIML Connect Friday: AI Consciousness
- Date: Fri, 14 Jun 2024
- Location: AIML
Jon spoke of the nature of consciousness and the prospects for conscious AI. An issue he raised is whether the 鈥榳hat-it-is-like鈥 of consciousness is a result of how brains process information or, by contrast, is a special material property of biological neural systems. If the former is true, we will have properly conscious AIs and robots in short order with all the ethical problems that raises.
AIML Research Seminar: The ghost of forecasts past
- Date: Tue, 11 Jun 2024
- Location: AIML
Numerical Weather Prediction (NWP) is experiencing a turbulent upheaval. Machine learning (ML) promises to alter every aspect of the process, but integration of the new, fast ML-driven forecast systems is going slowly.
[Read more about AIML Research Seminar: The ghost of forecasts past]
AIML Special Presentation: Does a farmer want AI? Developing a Trusted AI Agronomist
- Date: Mon, 3 Jun 2024
- Location: AIML
A path to a productive, resilient, and sustainable agricultural future lies in the successful integration of disruptive AI-driven agritechnology into decision-making processes across the food supply chain. These advanced solutions are crucial for assessing trade-offs and risks in a world increasingly affected by climate volatility. However, these solutions cannot come without a deeper understanding of the underlying appetite for such solutions.
AIML Research Seminar: From Data to Discoveries - machine learning and optimisation in space
- Date: Tue, 28 May 2024
- Location: AIML
During his time as internal research fellow at the European Space Agency, Marcus M盲rtens organised several open competitions that paved the way for applying modern machine learning (ML) techniques to space-related challenges. This talk provided an overview of this process from the original idea to the preparation of the datasets, the management of the actual competitions, and an analysis of the resulting aftermath.
AIML Special Presentation: Google Research Visit
- Date: Thu, 16 May 2024
- Location: AIML
Generative LLMs are transforming multiple industries and have proven to be robust for multitude of use cases across industries and settings. One of the key impediments to their widespread deployment is the cost of serving and its deployability across multiple devices/settings. In this talk, Grace and Prateek discussed the key challenges in improving efficiency of LLM serving and provided an overview of some of the key techniques to address the problem. They also discussed tandem transformers and HIRE, novel methods to speed up decoding in LLMs.听
[Read more about AIML Special Presentation: Google Research Visit]
CAR Special event - Data61
- Date: Tue, 7 May 2024
- Location: AIML
David and Lars presented an overview of their research interests and capabilities, highlighting their involvement in external projects. Afterwards, Dr Russell Tsuchida and Buse Turunctur discussed their research interests and possible collaborations.
AIML Special Presentation: Active Learning with Deep Neural Networks
- Date: Wed, 1 May 2024
- Location: AIML
In Active Learning the system gives select data to an expert to annotate, which is costly and should be minimised.听 Prof Butine proposes the first general Bayesian method to work well in this context, and his experiments show it is the only method consistently better than random. 听
[Read more about AIML Special Presentation: Active Learning with Deep Neural Networks]
AIML Research Seminar: Crater-based pose estimation for cislunar located spacecraft
- Date: Tue, 30 Apr 2024
- Location: AIML
In this presentation, Sofia demonstrated how we can estimate cislunar located spacecraft through a crater-based pose estimation pipeline. 听Her research focus lies in the final pose estimation step of the pipeline, where she has conclusively addressed the weaknesses of current pose estimation methods by developing a robust perspective-n-crater algorithm. As part of this research, Sofia interned for three months at Japan鈥檚 National Institute of Information and Communication Technology and discussed what it was like working and living in Japan.
AIML Special Presentation: Trustworthy AI
- Date: Mon, 29 Apr 2024
- Location: AIML
Out-of-distribution (OOD) detection aims to let a well-trained classifier tell what it does NOT know, instead of wrongly recognising an unknown object as a known one. For example, for a well-trained flower recognition model, we want it to tell users 鈥淚 don鈥檛 know鈥 when users show a car image to it, instead of telling users that it is a kind of flower. In this talk, Dr Liu presented one advance in OOD detection theory and two recent OOD scores: one based on in-distribution prior and the other based on the pre-trained vision-language model CLIP.