Nandi Schoots
Open Menu
Close Menu
Home
Selected work
Thesis
Contact
Publications
Any Deep ReLU Network is Shallow
Jun 26, 2023
Finding Sparse Initialisations using Neuroevolutionary Ticket Search (NeTS)
Jun 26, 2023
Low-Entropy Latent Variables Harm Out-of-Distribution Performance
Jun 24, 2023
Safety Properties of Inductive Logic Programming
Feb 24, 2021
The Propensity for Density in Feed-forward Models
Jan 1, 0001
Relating Piecewise Linear Kolmogorov Arnold Networks to ReLU Networks
Jan 1, 0001
Improving Activation Steering in Language Models with Mean-Centring
Jan 1, 0001
Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs
Jan 1, 0001
Extending Activation Steering to Broad Skills and Multiple Behaviours
Jan 1, 0001
Dissecting Language Models: Machine Unlearning via Selective Pruning
Jan 1, 0001