This is a past event
Hosted by King's College London.
The escalating complexity of AI models has resulted in soaring energy expenses for training and inference. These models also frequently yield unreliable outcomes, lacking the ability to address uncertainty in both models and data. Addressing these issues requires breakthroughs in algorithms, architectures, and fundamental computational units.
In this talk, Professor Bipin Rajendran will outline recent progress in creating efficient and reliable AI drawing inspiration from the computational architecture of the brain. He will describe their approach for developing brain-inspired algorithms, and in-memory computing architectures that employ nanoscale devices to implement deterministic as well as probabilistic AI models, opening up a path to reliable and efficient AI hardware.
Join in person or online.
Find out more and register here.
External event: The University of Aberdeen is a member of The Turing University Network, a network committed to offering UK universities the opportunity to engage and collaborate both with The Alan Turing Institute and its broader networks in academia, industry and the public sector. Discover more about the university becoming a member of The Turing University Network: Turing Universities Network | Research | The University of Aberdeen (abdn.ac.uk).