no code implementations • 14 Oct 2020 • Debajyoti Datta, Shashwat Kumar, Laura Barnes, Tom Fletcher
Using our approach, we explore difficult examples for several deep learning architectures.
no code implementations • 13 Dec 2018 • Line Kühnel, Alexis Arnaudon, Tom Fletcher, Stefan Sommer
We apply a stochastic generalisation of the Large Deformation Diffeomorphic Metric Mapping (LDDMM) framework to model differences in the evolution of anatomical objects detected in populations of image data.
no code implementations • 8 Oct 2018 • Hadi Salman, Payman Yadollahpour, Tom Fletcher, Kayhan Batmanghelich
We use a neural network to parametrize the smooth vector field and a recursive neural network (RNN) for approximating the solution of the ODE.
no code implementations • 19 May 2018 • Line Kuhnel, Tom Fletcher, Sarang Joshi, Stefan Sommer
Given data, deep generative models, such as variational autoencoders (VAE) and generative adversarial networks (GAN), train a lower dimensional latent representation of the data space.
no code implementations • NeurIPS 2013 • Miaomiao Zhang, Tom Fletcher
Principal geodesic analysis (PGA) is a generalization of principal component analysis (PCA) for dimensionality reduction of data on a Riemannian manifold.