My background is in the theory of deep learning, and during my PhD, I aim to use ideas of functional similarity and mechanistic interpretability to better understand neural networks and their outputs from a foundational perspective.
My previous research has focused on Network Compression, Knowledge Transfer and Machine Unlearning to strengthen both understanding and regulatory compliance of AI. Alongside my PhD, I am involved with improving policy practices for AI and as an AI Policy Fellow with the European Union. I have authored policy proposals that aim to streamline AI Governance.
Joining the UKRI Safe and Trusted PhD program was an obvious choice given its ardent commitment to delivering technological advancements while refusing to compromise on the robustness and safety of such systems. In a world where the mantra is “move fast and break things”, the STAI CDT is dedicated to picking up the pieces to make a more trustworthy and equitable future.
–
Undergraduate Qualification: BSc Computer Science, Queen Mary University of London
Masters Qualification: M.Phil Advanced Computer Science, University of Cambridge
Work Experience:
AI Policy Fellow, European Union.
Visiting Researcher in The Fundamentals of AI, Queen Mary University of London.
AI Safety Fellow, Cambridge AI Safety Hub.
AI Researcher, BIOREME Network.
AI Researcher, European Bioinformatics Institute.
LinkedIn: https://www.linkedin.com/in/israelfmw/
