7 Must-read Quora Machine Learning and Data Science Answers

Article by Rei Morikawa | May 01, 2019

Quora is an online platform where users can ask questions and connect with experts who contribute unique insights and quality answers. The questions are organized by topic, such as machine learning, natural language processing, and computer vision.

Quora has hundreds of millions of unique users monthly, and is available in non-English languages including Spanish, French, and Japanese.


In this post, we have compiled a list of Quora answers from machine learning experts sharing their practical advice about how to train and work on different models. We hope these answers give you deep insight and help you make progress on your own projects too. If you consistently find a particular contributor’s answers valuable on Quora, you can also follow them and receive notifications when they answer new questions. 


Best Quora Answers About Machine Learning and Data Science

“The 2 most famous languages in machine learning are Python and R …” Arighna Roy, PhD Computer Science


“Type checking and shape checking for training data must be done after preprocessing. It’s a very frequent source of bugs.” Roman Trusov, CTO at XIX.ai


“Feature engineer, feature encoding and data preprocessing. What kind of data is there? Is it only numerical? Are there categorical features which could be incorporated into the model? Heads up, categorical features can be considered any type of data which isn’t immediately available in numerical form …” Daniel Bourke, Machine Learning Engineer at Max Kelsen


“Gradient descent is a primitive algorithm. It merrily walks down the hill in the steepest direction until it gets to a bottom. Then it just stops …” Håkon Hapnes Strand, Data Scientist


“TensorFlow is a low-level library that allows you to build machine learning models (and other computations) using a set of simple operators, like add, matmul, concat …” Derek Murray, member of the TensorFlow team at Google


“I would recommend you to take a look at the final projects of machine learning related courses. Below is the list of the Stanford courses.” Vasily Konovalov, Software Engineer & Machine Learning/Natural Language Processing researcher


“The most important parts of mathematics you need to master in order to understand machine learning algorithms are: (1) Statistics and in particular bayesian statistics. This will help you understand algorithmic methods such as bayesian classification …” Alket Cecaj, Computer Science PhD

We hope you enjoyed these Quora machine learning questions and answers. I’m sure we couldn’t fit them all on this list, so let us know which ones we missed on Twitter.

Please be sure to subscribe to our newsletter below to keep up with all the latest in AI and machine learning.

Keep up with all the latest in machine learning
The Author
Rei Morikawa

Rei writes content for Lionbridge’s website, blog articles, and social media. Born and raised in Tokyo, but also studied abroad in the US. A huge people person, and passionate about long-distance running, traveling, and discovering new music on Spotify.


    Sign up to our newsletter for fresh developments from the world of training data. Lionbridge brings you interviews with industry experts, dataset collections and more.