Search Results for author: P. Thomas Fletcher

Found 7 papers, 1 papers with code

Deep Learning the Shape of the Brain Connectome

no code implementations6 Mar 2022 Haocheng Dai, Martin Bauer, P. Thomas Fletcher, Sarang C. Joshi

To statistically study the variability and differences between normal and abnormal brain connectomes, a mathematical model of the neural connections is required.

Integrated Construction of Multimodal Atlases with Structural Connectomes in the Space of Riemannian Metrics

1 code implementation20 Sep 2021 Kristen M. Campbell, Haocheng Dai, Zhe Su, Martin Bauer, P. Thomas Fletcher, Sarang C. Joshi

In order to enable population-level statistical analysis of the structural connectome, we propose representing a connectome as a Riemannian metric, which is a point on an infinite-dimensional manifold.

Structural Connectome Atlas Construction in the Space of Riemannian Metrics

no code implementations9 Mar 2021 Kristen M. Campbell, Haocheng Dai, Zhe Su, Martin Bauer, P. Thomas Fletcher, Sarang C. Joshi

The structural connectome is often represented by fiber bundles generated from various types of tractography.

The Adversarial Attack and Detection under the Fisher Information Metric

no code implementations9 Oct 2018 Chenxiao Zhao, P. Thomas Fletcher, Mixue Yu, Yaxin Peng, Guixu Zhang, Chaomin Shen

By considering the data space as a non-linear space with the Fisher information metric induced from a neural network, we first propose an adversarial attack algorithm termed one-step spectral attack (OSSA).

Adversarial Attack

The Riemannian Geometry of Deep Generative Models

no code implementations21 Nov 2017 Hang Shao, Abhishek Kumar, P. Thomas Fletcher

Deep generative models learn a mapping from a low dimensional latent space to a high-dimensional data space.

Translation

Local Group Invariant Representations via Orbit Embeddings

no code implementations6 Dec 2016 Anant Raj, Abhishek Kumar, Youssef Mroueh, P. Thomas Fletcher, Bernhard Schölkopf

We consider transformations that form a \emph{group} and propose an approach based on kernel methods to derive local group invariant representations.

Rotated MNIST

Cannot find the paper you are looking for? You can Submit a new open access paper.