Forget models, build a data flywheel | Machine Learning Monthly January 2021
As usual an unbelievable month on tour in the world of machine learning for January! Seems like the trend of the year is: multi-modal models, transformers taking over everything and machine learning deployment becoming mainstream (don't let your models die in notebooks, deploy them).
Machine Learning Monthly January 2021 - https://zerotomastery.io/blog/machine...
Support freeCodeCamp's Data Science Curriculum - https://www.freecodecamp.org/news/bui...
Connect elsewhere:
Web - https://dbourke.link/web
Get email updates on my work - https://dbourke.link/newsletter
Timestamps:
0:00 - Intro/hello
1:15 - freeCodeCamp's data science fund (donate if you can!)
2:57 - my upcoming TensorFlow course
3:54 - detecting hateful memes by Niklas Muennighoff
7:09 - Aurélien’s deep thoughts blog
9:14 - OpenAI’s massive January
10:12 - DALLE (creating images from text)
14:32 - CLIP (using text to help fix major problems in computer vision)
20:34 - Amit’s Papers with Video Chrome extension
22:30 - Bottleneck Transformers take over vision
25:16 - Bonus #1: Full Stack Deep Learning’s guide to transformers
25:59 - Made with ML’s pivot
29:13 - Awesome production machine learning
30:12 - Josh Tobin’s the missing piece of full-stack ML talk
33:26 - Bonus #2: Full Stack Deep Learning’s 2021 curriculum
35:02 - Apple’s system for delivering ML to 1 billion+ devices
40:05 - Outro/summary
#machinelearning #datascience
