Latest events

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.

AIML Special Presentation: Does a farmer want AI? Developing a Trusted AI Agronomist

Drs Sarah Hartman and Petra Kuhnert during their AIML presentation

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

Image for Marcus Märtens' presentation, June 2024

Date: Tue, 28 May 2024
Location: AIML

During his time as internal research fellow at the European Space Agency, Marcus Märtens 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.

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. 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.

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. 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’s 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 “I don’t know” 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.

AIML Research Seminar: Improving Efficiency of Foundation Models

Date: Tue, 16 Apr 2024
Location: AIML

Large deep learning models or foundation models such as chatGPT or GPT-4 have been the key factor in driving the recent new wave of AI breakthrough, resulting in huge social and economic impacts. However, even GPT-3 (the predecessor of ChatGPT) was trained on half a trillion words and equipped with 175 billion parameters, which required huge computing resource and energy consumption.

AIML Special Guest Presentation: Exploring the Earth and space with micro-satellites

Date: Wed, 3 Apr 2024
Location: AIML

In the past, space utilisation has required long preparation times and high budgets, but the 50 kg optical satellites we have developed and have successfully launched six times can be fabricated in a few years with a budget of 3-7 M USD and can be launched for 1-2 M USD, e.g. using carpool launch opportunities. This means that universities and relatively small companies can own and operate their own satellites, even if they are not national space organisations.

��˴�Ƭ