Issue #50
May 10, 2020
- 1. Covering science at dangerous speeds [cjr.org]
- 2. Google's medical AI was super accurate in a lab. Real life was a different story [technologyreview.com]
- 3. A high-performance topological machine learning toolbox in Python [github.com/giotto-ai]
- 4. scikit-network: Python package for the analysis of large graphs [scikit-network.readthedocs.io]
- 5. Seasonality of SARS-CoV-2: Will COVID-19 go away on its own in warmer weather? [ccdd.hsph.harvard.edu]
- 6. A visual explanation for regularization of linear models [explained.ai]
- 7. A foolproof way to shrink deep learning models [news.mit.edu]
- 8. A brief introduction to the beauty of Information Theory [notamonadtutorial.com]
- • Explainable Deep Learning: A Field Guide for the Uninitiated (N. Xie, G. Ras, M. van Gerven, D. Doran)
- • The Danish Gigaword Project (L. Strømberg-Derczynski, R. Baglini, M. H. Christiansen, M. R. Ciosici et al)
- • Deep learning of physical laws from scarce data (Z. Chen, Y. Liu, H. Sun)
- • Are the COVID19 restrictions really worth the cost? A comparison of estimated mortality in Australia from COVID19 and economic recession (N. W. Bailey, D. West)
- • Neural Networks and Value at Risk (A. Arimond, D. Borth, A. Hoepner, M. Klawunn, S. Weisheit)
- • A Primer on Private Statistics (G. Kamath, J. Ullman)
- • Weak ties strengthen anger contagion in social media (R. Fan, K. Xu, J. Zhao)
- • Bitcoin Transaction Networks: an overview of recent results (N. Vallarano, C. Tessone, T. Squartini)
Complete Statistical Theory of Learning (Vladimir Vapnik) | MIT Deep Learning Series
All our videos are also available in our YouTube playlist.
Enjoy the newsletter?
Forward it to a friend, or subscribe to get it straight to your inbox.
Subscribe Free