Nandi Schoots

Nandi Schoots

PhD student

Safe and Trusted AI

Biography

I’m searching for research questions that cut to the core of human understanding and hope to one day find natural laws that make highly specific predictions and apply in many contexts. In the mean-time I’m working on a variety of projects that piqued my interest.

I was one of the main organizers of the first AI Safety Camp.

Interests
  • The Science of Deep Learning
  • Inductive Biases in Neural Networks
  • Theory of Mind; decision-making; reasoning…
Education
  • PhD in Artificial Intelligence, 2024

    King's College London and Imperial College London

  • MSc in Mathematics

    Leiden University and Paris-Sud University

  • BSc in Mathematics

    Leiden University

Recent Publications

Quickly discover relevant content by filtering publications.
(2023). Any Deep ReLU Network is Shallow. (Preprint).

PDF

(2023). Finding Sparse Initialisations using Neuroevolutionary Ticket Search (NeTS). In ALIFE.

(2023). Low-Entropy Latent Variables Harm Out-of-Distribution Performance. In ICLR workshop - Domain Generalization.

PDF

(2021). Safety Properties of Inductive Logic Programming. AAAI workshop on AI Safety.

PDF

(2020). Learning to Communicate with Strangers via Channel Randomisation Methods. In NeurIPS workshop - Emergent Communication.

PDF

Contact