Data Science Roundup #52: Spotlight on Neural Networks! Plus, 21 Interview Answers You Need to Know.
🍻 One year of the Data Science Roundup! 🍾
This week's best data science articles
Q1. Explain what regularization is and why it is useful.
Q3. How would you validate a model you created to generate a predictive model of a quantitative outcome variable using multiple regression.
This might be the best data science study guide out there. It’s also a great personal check to find your own blind spots 🙈
Much of machine learning is more empirical than theoretical: we can prove that it works, but we’re not always sure why it works. Nowhere has this been more true than neural networks. Recently, two physicists published a paper positing an answer: the universe “favors certain classes of exceptionally simple probability distributions that deep learning is uniquely suited to model”. This is important.
Speaking of neural networks, this is an insanely useful resource for understanding the difference between various network topologies. Even if you’re not deep into neural networks on a daily basis, you’ve likely heard of RNNs, CNNs, Variational Autoencoders (VAEs), and more… Having not done a lot of work in this area myself, these differences were mostly lost on me. If you’re in the same boat, use this article as your translator. Not only does it have useful diagrams, but the author takes the time to explain the benefits and drawbacks of each topology.
I don’t typically include posts by investors, but I made an exception here. Matt Turck invests in Frontier Tech—"AI, IoT, AR, VR, drones, robotics, autonomous vehicles, space, genomics, neuroscience, and perhaps the blockchain.“ Matt makes the observation that: "Most of those areas have the same common core, which is the newly-found ability to capture, process and analyze massive amounts of data, cheaply and quickly enough.”
You probably knew this, but much of the cool stuff coming in our future is powered by data science. 👌👌
Wow: “In 2013, Airbnb had a small, centralized team of five data scientists serving the data needs of the company. Since then, they have grown to become one of the largest, most innovative startup teams with over 70 data scientists”. Growing a team from five to 70 in three years is really impressive.
Data viz of the week
Best climate change viz ever. Must see. Read to the end.
Thanks to our sponsors!
Fishtown Analytics is a boutique analytics consultancy serving high-growth, venture-funded startups. Have analytics questions? Let’s chat.
Developers shouldn’t have to write ETL scripts. Consolidate your data in minutes. No API maintenance, scripting, cron jobs, or JSON wrangling required.
The internet's most useful data science articles. Curated with ❤️ by Tristan Handy.
If you don't want these updates anymore, please unsubscribe here.
If you were forwarded this newsletter and you like it, you can subscribe here.
Powered by Revue
915 Spring Garden St., Suite 500, Philadelphia, PA 19123