Seminars

A decade ago, with the first multiqubit quantum computing devices, the prevailing opinion was that a clear winner would emerge amongst them. Today, not only is there no clear winner, but there are even more viable hardware platforms and models of quantum computation that they can execute than ever before.

The goal of Mechanistic Interpretability research is to explain how neural networks compute outputs in terms of their internal components. But how much progress has been made towards this goal?

A colouring of a graph with $k$ colours is an assignment of colours to vertices so that no edge is monochromatic. As it is well-known colouring with 2 colours is in P while colouring with $k > 2$ colours is NP-complete.

bla bla

Part III Thesis (Physics)

Explainability plays a pivotal role in building trust and fostering the adoption of artificial intelligence (AI) in healthcare, particularly in high-stakes domains like neuroscience where decisions directly affect patient outcomes.

AI has the potential to transform learning, creativity, and productivity. It represents a profound platform shift in technology – like the internet, or the shift to mobile. As with any transformational shift, AI will be (and already is) used for good and for evil.

Abstract: Wearable devices such as Apple Watch and Fitbit wristband allow users to track their health statistics around the clock. They have become increasingly popular over the past few years.

Idris is a functional programming language with first-class types, which allow properties to be expressed in the type system, and with an interactive type-driven editor which allows programs to be developed as a formal conversation with the machine.

*Abstract*