GoodAI Grant awarded to Pauching Yap, PhD Student at the UCL AI Centre

We are pleased to confirm that GoodAI has awarded a research grant to one of our current PhD students, Pauching Yap. Pauching is a final year PhD student on the Research Degree: Computer Science programme, supervised by David Barber and Brooks Paige. 

Pauching's reseach aims to create AI that can continually acquire knowledge in different domains as well as utilize past experiences to quickly adapt to new unseen tasks. Both continual learning, the ability to continually learn new things while avoiding catastrophic forgetting, and gradual learning, the ability to acquire new skills and solve new unseen tasks using previously acquired skills, are both problems of keen interest in the AI research world.

Pauching will take a novel approach to these problems, using the method of Bayesian Online Meta-Learning (BOML), which addresses the catastrophic forgetting problem on sequential tasks. The project will aim to extend the BOML framework using badger architecture principles to enable generalization to neural network topologies not seen during training, thus allowing adaptation to tasks that vary in input size, or enable solving tasks from various domains. Furthermore, the BOML framework will be adjusted to fit into GoodAI’s Badger architecture by encouraging communication between experts for a quick task adaptation. 

The grant is part of the ongoing GoodAI Grants initiative, which has awarded over $600,000 so far. The initiative is supporting research groups across the world that are solving problems related to GoodAI’s Badger architecture. The vision is that each research grant, along with the work of the GoodAI research team, will contribute in some way to basic AI research, and all together fill in some of the gaps in the roadmap to advanced, increasingly human-like AI.

David Barber, AI Centre Director and Pauching's supervisor said "Ensuring AI systems don't have to restart from scratch to solve each new problem is an interesting and important area. It's exciting to see Pauching's research being recognised and contributing to advances in basic AI research. Pauching richly deserves this award and I hope she'll continue to make further advances."

Congratulatons Pauching and thank you GoodAI!

More information can be found on the Good AI Blog Post: https://www.goodai.com/bayesian-online-meta-learning-boml-for-continual-gradual-learning/