Associate Professor in the Institute for Digital Communications, University of Edinburgh
Edinburgh, UK
Joined November 2011
- Tweets28
- Following151
- Followers69
- Likes217
An excellent opportunity in a world leading group.
We are offering a PhD position to work on model based deep-learning to solve inverse problems for multimodal imaging, fully funded 3.5 years for UK and international students. Don't miss out! See 👇 findaphd.com/phds/project/mo…
@HWU_SIPLab @HWUSinglePhoton @QOCIgroup
Mehrdad Yaghoobi retweeted
📢📢📢 Job Opportunity!
Join Dr Elliot J. Crowley and the Bayesian and Neural Systems Group as a postdoc in NAS and AutoML at the University of Edinburgh.
24-month funded position starting Autumn 2023. PhD in ML or related field required. Apply now: elxw.fa.em3.oraclecloud.com/…
Mehrdad Yaghoobi retweeted
📢📢 Release of DeepInverse library 📢📢
After months of intense work, we are releasing the first stable version of DeepInverse deepinv.github.io/deepinv/, a PyTorch library for solving inverse problems with deep learning.
with @HuraultSamuel, @MatthieuTerris and @ddongchen
A 🧵
Mehrdad Yaghoobi retweeted
Next talk by @myprojection on “self-supervised hyperspectral inpainting with the optimisation inspired deep neural network” at #iscs23
Mehrdad Yaghoobi retweeted
🎉 New Work: arxiv.org/abs/2305.17191🎉
Excited to announce, our new work "MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations" is accepted at #INTERSPEECH2023 and is now public. Links and overview below ⬇️. @tmh31 @myprojection @BudgettSam
A great opportunity to do a PhD in an excellent team.
Another fully funded PhD (4 years) available with me
@HeriotWatt_EPS. Interested in spiking networks and neuromorphic imaging and sensing? Do not hesitate to RT, get in touch and apply! Deadline 28/02. @HWU_SIPLab @ISSS_HW @IEEEimaging
findaphd.com/phds/project/ph…
Mehrdad Yaghoobi retweeted
Please re-tweet: PhD position in causality, representation learning & applications in healthcare. Fully funded international fees too (by @CanonMedicalEDI @RAEngNews). Co-supervised by @alisonQoneil. Join @SnchzPedro_ @Xiaoliu33745946 and others in VIOS.
findaphd.com/phds/project/ca…
Mehrdad Yaghoobi retweeted
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 🧵
Mehrdad Yaghoobi retweeted
Is few-shot meta-learning successful for general modalities? Find out how well your favourite meta-learner does in few-shot audio tasks in our new benchmark "MetaAudio"! cheggan.github.io/posts/2022…
This is our recent collaborative work, between Engineering and Chemistry in Edinburgh, with the support of industry. Looking forward to extending to other new- phase/material detection. @Stephan48909488 @ColinCa57082954
This Post is from an account that no longer exists. Learn more
Mehrdad Yaghoobi retweeted
In the first of our Winter Graduation Stories 2019, MSc Signal Processing and Communications student Xiao Liu explains why he chose to study at @EdinburghUni, picks his highlights of being a student and explains what he plans to do next. edin.ac/37uG9kr #EdinburghGrad✨🎓
Mehrdad Yaghoobi retweeted
Seeing a lot of confusion regarding these two terms in GAN papers lately.
Mode Collapse: When a large region of a model's input space maps to a small region around a single (often bad) sample.
Mode Dropping: When modes in the data are not represented in the output of the model.
Mehrdad Yaghoobi retweeted
Fully funded PhD still available in my group! Great opportunity to develop new computational methods for imaging through turbulence.@HWU_EPS @HWU_SIPLab @Leonardo_UK @CENSIS121 @ISSS_HW
Research Opportunity: PhD in computational imaging, fully funded from autumn 2019, led by @YoannAltmann @HWUEPS working on 2D/3D imaging. Supported by @CENSIS121 & @Leonardo_UK. @HWU_SIPLab @HWUSinglePhoton ow.ly/3Nm630peHkb
Mehrdad Yaghoobi retweeted
We are recruiting! Research Associate in Image Processing & Machine Learning for Microendoscopy: An exciting opportunity to develop algorithms for a breakthrough healthcare imaging system vacancies.ed.ac.uk/pls/coreh…. Healthcare Impact Partnership (EP/S025987/1)." @EPSRC_Proteus
Mehrdad Yaghoobi retweeted
“researchers’ careers depend more on publishing results with ‘impact’ than on publishing results that are correct” This is not a revelation but it is still shocking. You can read the full @nature article about research misconduct at Duke University here nature.com/articles/d41586-0…
Mehrdad Yaghoobi retweeted
Oldies but goldies: G. Cybenko, Approximations by superpositions of sigmoidal functions, 1989. Proves that a 1 hidden layer perceptron can approximate arbitrary continuous functions using a large enough number of neutrons. en.wikipedia.org/wiki/Univer… en.wikipedia.org/wiki/Multil…
Mehrdad Yaghoobi retweeted
Three good reasons to use black-box AI systems: science.sciencemag.org/conte…
Michael E. Davies: Inexact gradient projection and fast data driven comp... youtu.be/-2-M6NMud2c via @YouTube
