... | ... | @@ -18,27 +18,9 @@ If you’re interested in more details about the Journal Club, please subscribe |
|
|
|
|
|
## Next Meeting
|
|
|
|
|
|
### ! moved! 22 February 2021 Explainable Machine Learning
|
|
|
### 15 March 2021 Model uncertainty
|
|
|
|
|
|
Virtual Meeting using [BigBlueButton](https://webconf.fz-juelich.de/b/wen-mym-pj7)
|
|
|
|
|
|
* Unmasking Clever Hans predictors and assessing what machines really learn<br>
|
|
|
Sebastian Lapuschkin, Stephan Wäldchen, Alexander Binder, Grégoire Montavon, Wojciech Samek, Klaus-Robert Müller <br>
|
|
|
Nat Commun 10, 1096 (2019)<br>
|
|
|
https://doi.org/10.1038/s41467-019-08987-4<br>
|
|
|
6 pages
|
|
|
|
|
|
* Discovering physical concepts with neural networks<br>
|
|
|
Raban Iten, Tony Metger, Henrik Wilming, Lidia del Rio, Renato Renner <br>
|
|
|
Physical Review Letters, 124(1), 2020, 010508<br>
|
|
|
https://arxiv.org/abs/1807.10300<br>
|
|
|
5 pages + 11 pages Appendix :)
|
|
|
|
|
|
Intro by Tobias Tesch (IBG-3)
|
|
|
|
|
|
## Schedule for upcoming Meetings
|
|
|
|
|
|
### 15 March 2021 Model uncertainty
|
|
|
|
|
|
* What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?<br>
|
|
|
Alex Kendall, Yarin Gal<br>
|
... | ... | @@ -54,6 +36,8 @@ https://arxiv.org/abs/1505.05424<br> |
|
|
|
|
|
Intro by Clara Betancourt (JSC)
|
|
|
|
|
|
## Schedule for upcoming Meetings
|
|
|
|
|
|
### 19 April 2021 Model uncertainty
|
|
|
* A Simple Baseline for Bayesian Uncertainty in Deep Learning<br>
|
|
|
Wesley J. Maddox, Timur Garipov, Pavel Izmailov, Dmitry Vetrov, Andrew Gordon Wilson<br>
|
... | ... | @@ -68,6 +52,30 @@ https://arxiv.org/pdf/1907.06890.pdf |
|
|
|
|
|
## Past Meetings
|
|
|
|
|
|
### 22 February 2021 Explainable Machine Learning
|
|
|
|
|
|
* Unmasking Clever Hans predictors and assessing what machines really learn<br>
|
|
|
Sebastian Lapuschkin, Stephan Wäldchen, Alexander Binder, Grégoire Montavon, Wojciech Samek, Klaus-Robert Müller <br>
|
|
|
Nat Commun 10, 1096 (2019)<br>
|
|
|
https://doi.org/10.1038/s41467-019-08987-4<br>
|
|
|
6 pages
|
|
|
|
|
|
* Discovering physical concepts with neural networks<br>
|
|
|
Raban Iten, Tony Metger, Henrik Wilming, Lidia del Rio, Renato Renner <br>
|
|
|
Physical Review Letters, 124(1), 2020, 010508<br>
|
|
|
https://arxiv.org/abs/1807.10300<br>
|
|
|
5 pages + 11 pages Appendix :)
|
|
|
|
|
|
Intro by Tobias Tesch (IBG-3)
|
|
|
|
|
|
* slides tbd
|
|
|
* from the meeting:
|
|
|
* reminder to register for the Juelich Challenges Hackathon [[here](https://hifis-events.hzdr.de/event/51/)]
|
|
|
* follow up paper worth reading: <br>
|
|
|
Lundberg et al 2020, __From local explanations to global understanding with explainable AI for trees__, Nature Machine Intelligence 2, pages56–67(2020)
|
|
|
[link](https://www.nature.com/articles/s42256-019-0138-9)
|
|
|
|
|
|
|
|
|
### 18 January 2021 Explainable Machine Learning
|
|
|
|
|
|
* Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems<br>
|
... | ... | @@ -253,4 +261,4 @@ A training schedule using filter pruning and orthogonal reinitialization |
|
|
|
|
|
|
|
|
---
|
|
|
last change: 17.2.2021 sw |
|
|
last change: 22.2.2021 sw |