The beginner feels like everything is difficult. The expert knows that nothing is easy.
β FranΓ§ois Chollet (@fchollet) May 6, 2022
The beginner feels like everything is difficult. The expert knows that nothing is easy.
β FranΓ§ois Chollet (@fchollet) May 6, 2022
You might not believe it, but the following 6 machine learning books are fully free:
β Jean de Nyandwi (@Jeande_d) May 2, 2022
- Deep Learning
- Dive into Deep Learning
- Machine Learning Engineering
- Python Data Science Handbook
- Probabilistic Machine Learning
- Machine Learning Yearning
Here are their links 𧡠pic.twitter.com/TMEu5hB2MX
I've finally put my finger on why "gradual typing" is often so difficult to implement in established Python packages. The issue is that it runs entirely counter to the "Easier to Ask for Forgiveness than Permission" (EAFP) coding style long advocated in the Python language.
β Jake VanderPlas (@jakevdp) April 25, 2022
Programming languages: a cheat sheet. pic.twitter.com/k7m3bynbQZ
β Bojan Tunguz (@tunguz) April 25, 2022
Bayesians: "Join us! Updating prior believes is exactly how humans learn."
β Christoph Molnar (@ChristophMolnar) April 23, 2022
Causal inference: "Join us! Humans think in causal relationships."
Machine learning: "Join us! Models are black boxes and so are humans."
1/2
Exhaustive Survey of Rickrolling in Academic Literature
β AK (@ak92501) April 15, 2022
abs: https://t.co/pm0XBhwf0L
video: https://t.co/Mcli4ZYVUO pic.twitter.com/x4nkElT4BB
People who are competing on Kaggle. Are you calibrating your classifiers / proba scores at all? (E.g., using CalibratedClassifierCV, https://t.co/cS7zI5CFTX.) Do you find that it noticeably improves your ROC AUC? (cc @tunguz @svpino @JFPuget)
β Sebastian Raschka (@rasbt) April 13, 2022
'[Machine Learning] is no longer solo work, but teamwork. The corollary is this: discipline enables better collaborative work.'
β Sebastian Raschka (@rasbt) April 8, 2022
Great post by @ericmjl: https://t.co/sOzazojsfF
- conda envs
- git repos (for every project)
- cookiecutters
All the things I recommend & use!
niche problems with billions of daily users https://t.co/oRkAofyvKd
β hardmaru (@hardmaru) March 31, 2022
US AI researchers: Big models have loads of problems and it's mostly not appropriate for academia to develop them.
β Jack Clark (@jackclarkSF) March 29, 2022
Chinese AI researchers: Here's a 200 page roadmap for why big models are really important and why we should develop them https://t.co/TI2pl8Ra71
Iβve long thought that thinking only about the mean of a distribution is an indication of lack of sophisticated analytical thinking. This is a great illustration of that https://t.co/2i8vMYBdMQ
β JD Long (@CMastication) March 25, 2022
The longer I work on open-source ML tools, the more convinced I become in decoupling libraries.
β π©βπ» Paige Bailey #BlackLivesMatter (@DynamicWebPaige) March 23, 2022
Crafting simple, delightful, and composable user-facing APIs is *endlessly difficult*; you shouldn't also have to have a PhD in distributed systems in order to make those APIs scale.