33 citations · 45 across the 7 of their papers we have counts for
7 papers
Frequency and Generalisation of Periodic Activation Functions in Reinforcement Learning
Augustine N. Mavor-Parker, Matthew J. Sargent, Caswell Barry +2
Periodic activation functions, often referred to as learned Fourier features have been widely demonstrated to improve sample efficiency and stability in a variety of deep RL algori…
Towards Automated Circuit Discovery for Mechanistic Interpretability
Arthur Conmy, Augustine N. Mavor-Parker, Aengus Lynch +2
Through considerable effort and intuition, several recent works have reverse-engineered nontrivial behaviors of transformer models. This paper systematizes the mechanistic interpre…
Functional Connectome: Approximating Brain Networks with Artificial Neural Networks
Sihao Liu, Augustine N Mavor-Parker, Caswell Barry
We aimed to explore the capability of deep learning to approximate the function instantiated by biological neural circuits-the functional connectome. Using deep neural networks, we…
Using Forwards-Backwards Models to Approximate MDP Homomorphisms
Augustine N. Mavor-Parker, Matthew J. Sargent, Christian Pehle +3
Reinforcement learning agents must painstakingly learn through trial and error what sets of state-action pairs are value equivalent -- requiring an often prohibitively large amount…
How to Stay Curious while Avoiding Noisy TVs using Aleatoric Uncertainty Estimation
Augustine N. Mavor-Parker, Kimberly A. Young, Caswell Barry +1
Exploration in environments with sparse rewards is difficult for artificial agents. Curiosity driven learning -- using feed-forward prediction errors as intrinsic rewards -- has ac…
Scattering Networks on the Sphere for Scalable and Rotationally Equivariant Spherical CNNs
Jason D. McEwen, Christopher G. R. Wallis, Augustine N. Mavor-Parker
Convolutional neural networks (CNNs) constructed natively on the sphere have been developed recently and shown to be highly effective for the analysis of spherical data. While an e…
Efficient Generalized Spherical CNNs
Oliver J. Cobb, Christopher G. R. Wallis, Augustine N. Mavor-Parker +4
Many problems across computer vision and the natural sciences require the analysis of spherical data, for which representations may be learned efficiently by encoding equivariance…