Source: Deep Learning on Medium
D4S Sunday Briefing #28
A weekly newsletter with the latest developments in Data Science and Machine Learning and Artificial Intelligence.
Dec 8, 2019
Welcome to the 28th edition of the Sunday Briefing. This week we split our attention between finance
have exciting posts about NASA’s rules for coding, Information theory and forecasting using “humans in the loop”, and an in-depth look at the statistical mechanics of deep neural networks by one of the leaders in this field.
On the more academic front, we have reviews on Financial series forecasting using deep learning and neural machine translation. Finally, in the video of the week Sara Hooker gives us her perspective on the future of Deep Learning during a keynote on the Future of Finance conference.
On a different note, we are happy to announce the first ever edition of a 2 day training event on Time series modeling with ML and Deep Learning approaches on Mar 15–16, 2020 during the San Jose edition of O’Reilly’s AI/Strata conference.
If you think one of your friends or colleagues would enjoy this newsletter, just go ahead and forward this email to them and help us grow!
The D4S team
Tutorials and blog posts that came across our desk this week.
- Understanding Transfer Learning for Medical Imaging [ai.googleblog.com]
- Biased Algorithms Are Easier to Fix Than Biased People [nytimes.com]
- Towards a new theory of learning: Statistical Mechanics of deep neural networks [calculatedcontent.com]
- The Power of 10 — NASA’s Rules for Coding [medium.com/better-programming]
- Humans-in-the-loop forecasting: integrating data science and business planning [unofficialgoogledatascience.com]
- Better intuition for information theory [blackhc.net]
- An Epidemic of AI Misinformation [thegradient.pub]
Fresh off the press:
Some of the most interesting academic papers published recently.
- Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005–2019 (O. B. Sezer, M. U. Gudelek, A. M. Ozbayoglu)
- Neural Machine Translation: A Review (F. Stahlberg)
- Universality of power-law exponents by means of maximum-likelihood estimation
(V. Navas-Portella, Á. González, I. Serra, E. Vives, Á. Corral)
- Using Machine Learning to Assess Short Term Causal Dependence and Infer Network Links (A. Banerjee, J. Pathak, R. Roy, J. G. Restrepo, E. Ott)
- Scalable Graph Algorithms (C. Schulz)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library (A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Köpf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, S. Chintala)
Video of the week:
Interesting discussions, ideas or tutorials that came across our desk.
The Future of Deep Learning
Opportunities to learn from us
- Dec 11, 2019 — Deep Learning From Scratch [Register]
- Jan 17, 2019 — Time Series for Everyone [Register] 🆕
- Jan 27, 2019 — Applied Probability Theory for Everyone [Coming Soon]
- Mar 15–16, 2019 — Time series modeling: ML and deep learning approaches — Strata/AI [Register] 🆕
Thank you for subscribing to our weekly newsletter with a quick overview of the world of Data Science and Machine Learning. Please share with your contacts to help us grow!
Publishes on Sunday.
Copyright © 2019 Data For Science, Inc, All rights reserved.