Vlado Menkovski

100 posts

Vlado Menkovski banner
Vlado Menkovski

Vlado Menkovski

@vlamen

Assistant Professor at @TUeindhoven

Eindhoven, Netherlands Katılım Aralık 2008
275 Takip Edilen160 Takipçiler
Vlado Menkovski
Vlado Menkovski@vlamen·
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…
English
0
4
7
0
Vlado Menkovski retweetledi
Loek Tonnaer
Loek Tonnaer@LoekTonnaer·
For more details, we invite you to read the full paper, or come talk to us at ICML 2022! 10/10 🧵
English
0
1
0
0
Vlado Menkovski retweetledi
Loek Tonnaer
Loek Tonnaer@LoekTonnaer·
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/
Loek Tonnaer tweet media
English
1
1
0
0
Vlado Menkovski retweetledi
Loek Tonnaer
Loek Tonnaer@LoekTonnaer·
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/
English
1
1
0
0
Vlado Menkovski retweetledi
Loek Tonnaer
Loek Tonnaer@LoekTonnaer·
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/
Loek Tonnaer tweet media
English
1
1
1
0
Vlado Menkovski retweetledi
Loek Tonnaer
Loek Tonnaer@LoekTonnaer·
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/
English
1
1
1
0
Vlado Menkovski retweetledi
Loek Tonnaer
Loek Tonnaer@LoekTonnaer·
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/
English
1
1
0
0
Vlado Menkovski retweetledi
Loek Tonnaer
Loek Tonnaer@LoekTonnaer·
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/
English
1
1
0
0
Vlado Menkovski retweetledi
Loek Tonnaer
Loek Tonnaer@LoekTonnaer·
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/
English
1
1
0
0
Vlado Menkovski retweetledi
Loek Tonnaer
Loek Tonnaer@LoekTonnaer·
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/
English
1
1
0
0
Vlado Menkovski
Vlado Menkovski@vlamen·
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… via @TU/e
English
0
8
14
0
Vlado Menkovski retweetledi
microRNApapers
microRNApapers@microRNA_papers·
Detection of pre-microRNA with Convolutional Neural Networks dlvr.it/RJDLDR
English
0
2
1
0