It isn’t cheap to build the systems that show you what’s coming at you.
— Tim Harford (@TimHarford) February 5, 2021
But failing to build them? That’s far more expensive.
18/https://t.co/Bzjqr59yuW
It isn’t cheap to build the systems that show you what’s coming at you.
— Tim Harford (@TimHarford) February 5, 2021
But failing to build them? That’s far more expensive.
18/https://t.co/Bzjqr59yuW
Lightning made the mistake of relying on inheritance instead of callbacks, not realizing that inheritance has fundamental well-known limitations for extensibility.
— Jeremy Howard (@jeremyphoward) February 5, 2021
They even boasted about this.
Later, they were forced to add callbacks. Oops. pic.twitter.com/w7g7XnRl6t
This is a really good example of really bad survey design. The two prior questions to "should Cruz resign" are clearly priming respondents with the information the survey writers want to convey in a biasing manner. It should not be taken at face value. pic.twitter.com/hxG9XeeK3o
— Natalie Jackson (@nataliemj10) February 3, 2021
A useful distinction:
— Tim Harford (@TimHarford) February 1, 2021
Misinformation: incorrect or misleading information.
Disinformation: false information deliberately and often covertly spread in order to influence public opinion or obscure the truth.
Source: Merriam-Webster dictionary.
What do you call a machine learning model that perfectly predicts the training data, but does not work for unseen data?
— Christoph Molnar (@ChristophMolnar) February 1, 2021
A database
Every founder loves to complain that hiring is hard, but my experience is that hiring is work but isn't hard. Throw garbage like this out the window and think about what your team needs to accomplish and what it'll take to get you there. https://t.co/3S1eRgK0OU
— Hilary Mason (@hmason) January 31, 2021
The majority of U.S. adults prefer to do away with the #ElectoralCollege, with conservatives being the lone holdout. #dataviz
— Randy Olson (@randal_olson) January 30, 2021
Source: https://t.co/HarvHl73Mb pic.twitter.com/V5hLSZhxol
Still the best learning path for machine learning:
— Chris Albon (@chrisalbon) January 29, 2021
- A Mathematics Course for Political and Social Research
- Introduction to Statistical Learning
- Elements of Statistical Learning
- Deep Learning
Lots of directions you can take your learning after that.
Three rules of thumb for machine learning:
— Thomas (@evolvingstuff) January 28, 2021
1) be skeptical of good results
2) be skeptical of bad results
3) be skeptical of mediocre results
Piece of advice that helped me: Pay attention to how you feel when interacting with folks. Do they make you feel excited? Smart? Stupid? Lazy?
— Chris Albon (@chrisalbon) January 28, 2021
One of the highest value things you can do for yourself is shadowbanning from your life folks who makes you feel worse about yourself.
When reading a paper I can skim through a lot by just asking 5 simple questions:
— Eric Jang 🇺🇸🇹🇼 (@ericjang11) January 26, 2021
1 What are the inputs ?
2 What are the outputs ?
3 What loss supervises the output predictions and what assumptions about the world does this make?
I'm with @fchollet on this. There're some best-practices on creating and organizing data that experienced applied ML people use, but we still need to flesh out and widely disseminate these ideas. This will be key to getting more ML systems deployed. https://t.co/wJQEwNU6SX
— Andrew Ng (@AndrewYNg) January 25, 2021