15 citations · 34 across the 14 of their papers we have counts for
4 papers · 1 filter
On skip connections and normalisation layers in deep optimisation
Lachlan Ewen MacDonald, Jack Valmadre, Hemanth Saratchandran +1
We introduce a general theoretical framework, designed for the study of gradient optimisation of deep neural networks, that encompasses ubiquitous architecture choices including ba…
On Quantizing Implicit Neural Representations
Cameron Gordon, Shin-Fang Chng, Lachlan MacDonald +1
The role of quantization within implicit/coordinate neural networks is still not fully understood. We note that using a canonical fixed quantization scheme during training produces…
How You Start Matters for Generalization
Sameera Ramasinghe, Lachlan MacDonald, Moshiur Farazi +2
Characterizing the remarkable generalization properties of over-parameterized neural networks remains an open problem. In this paper, we promote a shift of focus towards initializa…
On Regularizing Coordinate-MLPs
Sameera Ramasinghe, Lachlan MacDonald, Simon Lucey
We show that typical implicit regularization assumptions for deep neural networks (for regression) do not hold for coordinate-MLPs, a family of MLPs that are now ubiquitous in comp…