Copy

Issue #33

Jan 12, 2020
Dear friends,

Welcome to the latest issue of the Sunday Briefing. This week we look at connections between Physics and ML, the limitation of ML when applied to Time-Series data and a new library to apply Unsupervised ML algorithms to Graph and Network data.

We explore the Interpretability of Neural Networks and a survey of recent application of AI for Social Good and financial applications with a post on Pairs Trading in the crypto space and the video of the week where Marcos Lopez de Prado discusses how we can Uncover Behavioral Biases with Machine Learning.

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!

Semper discentes,

The D4S team
As we announced a few weeks ago, we are preparing a few changes to the format and content of the newsletter. Today we are happy to announce one of the biggest one. Starting later this month, we will be posting (here) our very own blog articles. Among other one-off type articles exploring different ideas, we will have series that cover the content of books in a programmatic way. These will serve both as inspiration to future training events and as clarification and an expansion of existing content. 
 
The first book we will cover will be Judea Pearls's Causal Inference in Statistics - A Primer (affiliate link) a short and to the point introduction to Causality.  We invite you to follow along and send use your comments and suggestions. Naturally, having a physical copy of the book is not a requirement, but it's highly recommended as it makes it easier to follow along.

Top Links:

Tutorials and blog posts that came across our desk this week.
  1. Generative adversarial networks: What GANs are and how they’ve evolved [venturebeat.com]
  2. An Idea From Physics Helps AI See in Higher Dimensions [quantamagazine.org]
  3. Machine Learning Can't Handle Long-Term Time-Series Data [lesswrong.com]
  4. Karate Club is an unsupervised machine learning extension library for NetworkX [github.com/benedekrozemberczki]
  5. Tutorial: Python Regex (Regular Expressions) for Data Scientists [dataquest.io]
  6. Pairs Trading with Cryptocurrencies [towardsdatascience.com]
  7. Markov Chain Monte Carlo - A visual interpretation with Python [medium.com/analytics-vidhya]

Fresh off the press:

Some of the most interesting academic papers published recently.

Video of the week:

Interesting discussions, ideas or tutorials that came across our desk.


Uncovering Behavioural Biases with ML
https://www.youtube.com/watch?v=ncqnDl1VM-c

Upcoming Events:

Opportunities to learn from us
  1. Jan 17, 2020 - Time Series for Everyone [SOLD OUT] 
  2. Jan 27, 2020 - Applied Probability Theory for Everyone [Register] 
  3. Feb 10, 2020 - Natural Language Processing (NLP) for Everyone[Register] 🆕
  4. Feb 28, 2020 - Graphs and Network Algorithms for Everyone [Register] 🆕
  5. Mar 15-16, 2020 - 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.
Share
Tweet
Share
Forward
Twitter
Website
Email
Copyright © 2020 Data For Science, Inc, All rights reserved.


Want to change how you receive these emails?
You can update your preferences or unsubscribe from this list.

Email Marketing Powered by Mailchimp