Assistant Professor at @TUeindhoven
Joined December 2008
- Tweets 100
- Following 275
- Followers 159
- Likes 85
6 Photos and videos
19 Jun 2023
Very excited to share this! Looking for candidates for a #PhD position on the intersection of #GenerativeAI and Material Science. Supervised by Prof. Sofia Calero and co-supervised by me. jobs.tue.nl/en/vacancy/phd-i…
1
5
14
1,430
29 Jun 2022
An excellent opportunity to work on the intersection of ML and Physics. A vacancy on Machine Learning-based Simulation for Materials Discovery. Supervised by prof. Sofia Calero and co-supervised by me: jobs.tue.nl/en/vacancy/phd-o…
4
7
Vlado Menkovski retweeted
28 Jun 2022
For more details, we invite you to read the full paper, or come talk to us at ICML 2022!
10/10 🧵
1
Vlado Menkovski retweeted
28 Jun 2022
3) LSBD representations also satisfy previous disentanglement notions:
Good scores for D_LSBD (lower is better) typically imply good scores on traditional disentanglement metrics (higher is better), even if the reverse is not true.
9/
1
1
Vlado Menkovski retweeted
28 Jun 2022
2) LSBD-VAE and other LSBD methods *can* learn LSBD representations with limited supervision on transformations:
Methods that specifically target LSBD indeed score better on D_LSBD.
8/
1
1
Vlado Menkovski retweeted
28 Jun 2022
1) Traditional disentanglement methods don't learn LSBD representations:
Methods without a notion of the underlying symmetry group structure don't score well on D_LSBD, even if they do score well on traditional disentanglement metrics.
7/
1
1
1
Vlado Menkovski retweeted
28 Jun 2022
We perform experiments on a number of datasets with underlying symmetries, using our own LSBD-VAE and other LSBD-oriented methods, as well as various traditional disentanglement methods. From this we draw 3 main conclusions:
6/
1
1
1
Vlado Menkovski retweeted
28 Jun 2022
We show an intuitive justification of our D_LSBD metric, as well as its theoretical derivation. We also provide a practical implementation to compute D_LSBD for SO(2) symmetry groups of 2D rotations.
5/
1
1
Vlado Menkovski retweeted
28 Jun 2022
In our paper we present the following contributions:
i) D_LSBD, a well-formalized general metric to quantify LSBD in learned representations.
ii) LSBD-VAE, a weakly-supervised method to learn LSBD representations under certain assumptions.
4/
1
1
Vlado Menkovski retweeted
28 Jun 2022
However, there is currently no metric to quantify LSBD. Such a metric is crucial to evaluate methods aimed at learning LSBD, and to compare to previous notions of disentanglement.
3/
1
1
Vlado Menkovski retweeted
28 Jun 2022
Disentanglement is an important goal in representation learning, but there is no consensus on a formal definition. Higgins et al. (2018) propose such a definition based on the idea that real-world symmetries provide a structure to disentangle, which we refer to as LSBD.
2/
1
1
Vlado Menkovski retweeted
28 Jun 2022
Our paper "Quantifying and Learning Linear Symmetry-Based Disentanglement" got accepted at #ICML2022 @icmlconf!🥳🎉
Congrats to co-authors @tezcatlipocta (joint first), @vlamen, Mike Holenderski & Jim Portegies.
Paper: arxiv.org/abs/2011.06070
Code: github.com/luis-armando-pere…
1/🧵
2
2
5
10 May 2022
The @FullyChargedShw visits Eindhoven and @SolarEHV to check out Stella Vita the solar camper youtu.be/4vHuldVlpFA
1
5
Vlado Menkovski retweeted
6 May 2021
We have a vacancy for PhD in Artificial Intelligence for Computational Pathology.
Goal: develop new methods for end-to-end training of DL models from whole slide images with application in oncology.
#digitalpathology #deeplearning #machinelearning #AI
jobs.tue.nl/en/vacancy/phd-i…
1
14
20
22 Apr 2021
Can Machine Learning be a driver for scientific discovery? Join our multidisciplinary team of scientists and help us push Machine Learning forward to drive progress in natural sciences! jobs.tue.nl/en/vacancy/phd-p… via @TU/e
8
14
Vlado Menkovski retweeted
24 Jul 2020
Pedestrian orientation dynamics from high-fidelity measurements.
Open Access on Scientific Reports
nature.com/articles/s41598-0…
with J willems, @vlamen @ftoschi
2
5
Vlado Menkovski retweeted
15 Jan 2020
New preprint: "Pedestrian orientation dynamics from high-fidelity measurements"
researchgate.net/publication…
1
2
9
Vlado Menkovski retweeted
13 Nov 2019
Detection of pre-microRNA with Convolutional Neural Networks dlvr.it/RJDLDR
2
1
Vlado Menkovski retweeted
14 Nov 2019
New preprint available 😀 "Deep learning velocity signals allows to quantify turbulence intensity"
arxiv.org/abs/1911.05718
with @vlamen, Roberto Benzi and @ftoschi
1
5