From this episode you'll learn:
- How does Bayesian methods work
- How do machines reason under uncertainty and how to represent knowledge
- Why Machine Learning models are still largely superficial
- Why we should not be focusing on the "intelligence" part of the AI but rather seek practical applications
About the guest: David Barber received a BA in Mathematics from Cambridge University and subsequently a PhD in Theoretical Physics (Statistical Mechanics) from Edinburgh University. He is Director of the UCL Centre for Artificial Intelligence, which aims to develop next generation AI techniques. He has broad research interests related to the application of probabilistic modelling and reasoning. David is also a Fellow of the Alan Turing Institute and the CSO of re:infer, an AI spin-out from UCL.
