Michael P. Sheehan

65 posts

Michael P. Sheehan banner
Michael P. Sheehan

Michael P. Sheehan

@mpsheehan1995

PhD student researching Statistical and Compressive Learning at the University of Edinburgh.

Edinburgh Katılım Kasım 2017
139 Takip Edilen48 Takipçiler
Michael P. Sheehan retweetledi
Low-rank Jack (go mathstodon)
Low-rank Jack (go mathstodon)@jacquesdurden·
An open faculty position in "Computational Mathematics and Data Science" is announced in the ICTEAM Institute of the University of Louvain, with an application deadline on November 14, 2022. jobs.uclouvain.be/PersonnelAcade…
English
0
6
5
0
Michael P. Sheehan retweetledi
Dongdong Chen
Dongdong Chen@ddongchen·
🥳Our paper "Unsupervised Learning From Incomplete Measurements for Inverse Problems" was accepted to #NeurIPS2022. We present necessary and sufficient conditions for learning the signal model + a novel self-supervised Multi-Operator Imaging (MOI) method. arxiv.org/abs/2201.12151
English
2
1
10
0
Michael P. Sheehan retweetledi
Sotirios (Sotos) Tsaftaris
Sotirios (Sotos) Tsaftaris@STsaftaris·
Please retweet widely. Looking for a postdoc in representation learning. We want to learn good representations with (causal) generative models with rare/imbalanced data. You will work with bright minds, on a prestigious grant and interact with industry. DM me for more info.
English
0
35
35
0
Michael P. Sheehan retweetledi
Julián Tachella
Julián Tachella@TachellaJulian·
Which dataset would you choose for training the reconstruction net of an imaging system? 1. Pairs of images+measurements 2. Just all raw measurements Spoiler alert: the obvious answer is incorrect - a thread 🧵
Julián Tachella tweet media
English
1
10
20
0
Michael P. Sheehan retweetledi
Julián Tachella
Julián Tachella@TachellaJulian·
Attending #CVPR2022? Interested in imaging inverse problems? @ddongchen will be presenting our work in fully unsupervised learning for imaging inverse problems at Oral 2.1.3: Low-Level Vision (Great Hall B-C)
English
1
3
13
0
Michael P. Sheehan retweetledi
School of Engineering
School of Engineering@SchoolOfEng_UoE·
Our researchers scooped Best Student Paper at @ieeeICASSP for a #lidar breakthrough that could bring self-driving cars closer to market. Dr Mikey Sheehan, Prof Mike Davies & Dr Julián Tachella are working with @IbeoAutomotive to commercialise the tech. edin.ac/3MoJ7dz
GIF
English
0
1
5
0
Michael P. Sheehan retweetledi
IEEE ICASSP
IEEE ICASSP@ieeeICASSP·
Best Student Paper Awards! Congratulations to all the award winning authors!! (2/2) #ICASSP2022
IEEE ICASSP tweet mediaIEEE ICASSP tweet mediaIEEE ICASSP tweet media
English
0
2
7
0
Michael P. Sheehan retweetledi
Julián Tachella
Julián Tachella@TachellaJulian·
Want to solve your imaging problem with deep learning but no ground-truth data for training? Good news🥳! Learning from noisy and incomplete measurement data alone is possible: "Sampling Theorems for Unsupervised Learning in Linear Inverse Problems" arxiv.org/abs/2203.12513 1/4
English
2
9
26
0
Michael P. Sheehan retweetledi
Pedro P. Sanchez
Pedro P. Sanchez@SnchzPedro_·
(1/3) I am happy to share that our paper "Diffusion Causal Models for Counterfactual Estimation" will be presented next week at @CLeaR_2022. Check poster session 1 (11/04 - 4pm) or our 90s video! Huge thanks to @STsaftaris and the rest of the team at vios.science!
Pedro P. Sanchez tweet media
English
1
3
10
0
Michael P. Sheehan retweetledi
Dongdong Chen
Dongdong Chen@ddongchen·
Check our latest theory paper (with @TachellaJulian and Mike Davies) on unsupervised learning in inverse problems. This is the first-ever work presents necessary and sufficient sampling conditions for learning the signal model from partial measurements! arxiv.org/abs/2203.12513
English
1
2
4
0
Michael P. Sheehan retweetledi
Peyman Milanfar
Peyman Milanfar@docmilanfar·
This isn’t a scene from Tenet. It’s a great example of critical-rate sampling. Temporal aliasing occurs when the scene changes faster than camera frame rate. ‘Critical sampling’ is when the scene changes exactly as fast as the camera frame rate. twitter.com/ScienceVids_/s…
English
7
50
447
0
Michael P. Sheehan retweetledi
Stat.ML Papers
Stat.ML Papers@StatMLPapers·
Mean Nystr\"om Embeddings for Adaptive Compressive Learning. (arXiv:2110.10996v1 [stat.ML]) ift.tt/2Zib83Z
English
0
3
3
0