Latest events

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

Dana Rawls — Thu, 27 Jun 2024 10:50:46 +0930

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: The ghost of forecasts past

Dana Rawls — Thu, 27 Jun 2024 10:36:28 +0930

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 Connect Friday: AI Consciousness

Dana Rawls — Wed, 26 Jun 2024 09:15:40 +0930

Jon spoke of the nature of consciousness and the prospects for conscious AI. An issue he raised is whether the ‘what-it-is-like’ 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 Special Presentation: Learning Spatial context-aware Global Visual Feature Representation for Instance Image Retrieval

Dana Rawls — Tue, 25 Jun 2024 16:36:42 +0930

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 Research Seminar: Real-time Prediction for Non-stationary Data Streams

Dana Rawls — Tue, 25 Jun 2024 16:31:15 +0930

This talk focused on one of the most challenging issues in non-stationary data streams, known as concept drift. Concept drift occurs when the pattern of data changes over time, making models trained on historical data less effective at predicting new data patterns. This inability to adapt compromises the performance of well-trained machine learning models. From the perspective of concept drift adaptation, this presentation will introduce three general strategies for updating learned models with newly arrived data, aimed at mitigating the impact of concept drift.