I made a playlist of 11 short videos (most are 7-13 mins long) on Ethics in Machine Learning
— Rachel Thomas (@math_rachel) December 26, 2020
This is from my 2 hrs ethics lecture in Practical Deep Learning for Coders v4. I thought these short videos would be easier to watch, share, or skip aroundhttps://t.co/bLHhdPLch4 pic.twitter.com/eQIVwtJ38k
- How Transformers work in deep learning and NLP: an intuitive introduction https://t.co/3jCQ302heb
— /MachineLearning (@slashML) December 26, 2020
[FREE 185-page PDF]
— Kirk Borne (@KirkDBorne) December 25, 2020
Comprehensive Guide to #MachineLearning for #DataScientists → https://t.co/iZsREscT9v
——————#BigData #DataScience #AI #AppliedMathematics #DataMining #Mathematics #Algorithms #NeuralNetworks #DeepLearning #LinearAlgebra #Statistics #Calculus #abdsc pic.twitter.com/tiLvFW4nZw
Efficient transformer architectures for vision.
— Yann LeCun (@ylecun) December 24, 2020
Open source. https://t.co/MTCgPRgr6k
Here are the best data visualization projects of 2020. https://t.co/0cHIFof4ns
— Nathan Yau (@flowingdata) December 24, 2020
Training data-efficient image transformers & distillation through attention
— AK (@ak92501) December 24, 2020
pdf: https://t.co/52o44tGC5G
abs: https://t.co/XohbkS7kq5
github: https://t.co/KpkMSwfKdp pic.twitter.com/KP24f00vT4
And for research popularity, @gradientpub had a nice post last year (would be great to see 2020 as a data point) -- for some reason they deleted it or moved the URL pic.twitter.com/PDbIn8szXW
— Sebastian Raschka (@rasbt) December 23, 2020
Is it possible to do runtime type checking in python without mypy? Why, Yes! See fastcore.basics.typed
— Hamel Husain (@HamelHusain) December 23, 2020
🧵👇 pic.twitter.com/ZFN3XZIuiq
My favorite tidyr function pic.twitter.com/Ta1npxN8qR
— David Robinson (@drob) December 23, 2020
One interesting (but incomplete) measure of the state of the deep learning bubble. While PyTorch has caught up with TensorFlow, aggregate interest in DL frameworks seems to be maybe half what it was at the peak. I can imagine many interpretations, share yours. pic.twitter.com/adQwBeNsVp
— Zachary Lipton (@zacharylipton) December 23, 2020
So what works? The #1 thing to do is to make sure that the Black women at your company actually have a fair shot at success. This also means you will have to get rid of the people who are actively sabotaging them 6/https://t.co/NkVc5Yseo9 pic.twitter.com/SMtukbip9v
— Rachel Thomas (@math_rachel) December 23, 2020
Is your model fast?
— Chip Huyen (@chipro) December 23, 2020
No
Is it cheap?
No
Does it at least solve our problem?
No
…
But it’s StAtE oF tHe ArT
