| |
|
|
May 29 · Issue #17 · View online
Curated essays about the future of Data Science. Production Data Science and learning resources for continuous learning. Covers Data Science, Data Engineering, MLOps & DataOps. Curated by people at https://nibble.ai/
|
|
|
I cannot overstress the importance of pre-analysis work, particularly understanding the problem. Without a clearly articulated problem statement, the ensuing work is just a fishing expedition.
|
|
Do Your Data Scientists Know the ‘Why’ Behind Their Work?
|
Tukey, Design Thinking, and Better Questions Roger Peng, the author of this post, reads John Tukey’s paper “The Future of Data Analysis” every year. Though it’s a very good read, 62 pages might be a bit too much to pack within your busy day, just get started with Roger’s post Then you can just started with Roger’s post instead. Far better an approximate answer to the right question, which is often vague, than an exact answer to the wrong question, which can always be made precise.
|
|
|
How to Deploy Machine Learning Models There is complexity in the deployment of machine learning models. This guide aims to at the very least make you aware of where this complexity comes from, and should provide you with useful tools and heuristics to combat this complexity. Software development best practices in a deep learning environment It’s hard to apply SE best practices when working in a deep learning environment: rapidly evolving frameworks, data and configuration management, etc.. In this post, Per John from Kepler Vision Technologies present an analysis of said obstacles and the measures they take to overcome them at Kepler Vision Technologies. |
|
|
Cheatsheets for Stanford’s CS221: Artificial Intelligence A summary of Machine Learning fundamentals As a continuity, this series by Jonathan Hui that reviews the fundamentals topics you should know when working in data science: information theory, probability, HMM, GMM, etc.
|
Hands-on introduction to Convolutional Neural Networks A 2-part walkthrough of Convolutional Neural Networks, including what they are, how they work, why they’re useful, how to train them, and how to build one from scratch in Python. Part 1 and part 2. |
A summary of Machine Learning fundamentals A bit similar to the previous item, we’ve found this 2-part series by Jonathan Hui that reviews the fundamentals topics you should know when working in data science: information theory, probability, HMM, GMM, etc.
|
Hands-on tutorial for Convolutional Neural Networks Apart from creating and selling multiplayer (.io) web games, Victor Zhou also write about machine learning. I really love his simple guide to what CNNs are, how they work, and how to build one from scratch in Python. Get started with part 1 of 2 here. |
Just enough Scala for Spark I’d like to dive deeper into Scala and I got to discover this excellent tutorial by Dean Wampler from Lightbend during a meetup in Paris. As the name suggest, it’s made to that you learn enough Scala to get started using it for Spark |
|
|
|
Did you enjoy this issue?
|
|
|
|
In order to unsubscribe, click here.
If you were forwarded this newsletter and you like it, you can subscribe here.
|
|
|
|
|
|
