This is a brand new podcast dedicated to #MLOps. I had the privilege of kicking it off with some very talented friends 👇
— Hamel Husain (@HamelHusain) February 20, 2021
If you are new to MLOps, definitely check this out https://t.co/SEfA7Zjgl7
This is a brand new podcast dedicated to #MLOps. I had the privilege of kicking it off with some very talented friends 👇
— Hamel Husain (@HamelHusain) February 20, 2021
If you are new to MLOps, definitely check this out https://t.co/SEfA7Zjgl7
🐍: Ever wondered what __𝚖𝚛𝚘__ is?
— Radek Osmulski (@radekosmulski) February 20, 2021
It is the method resolution order (gets populated upon object creation)
In OOP, you look up the inheritance chain for a method that is called. This is the lookup chain 🙂
Quite fun and useful for understanding what something can do! pic.twitter.com/6LPd18FgBo
LambdaNetworks: Modeling long-range Interactions without Attention
— hardmaru (@hardmaru) February 20, 2021
Self-Attention has a new challenger❗️https://t.co/hLG6mwmQF5 pic.twitter.com/N0ll4JWHWC
Samy Bengio (a director at Google AI w/ 300 reports, who spoke up for Timnit) is being pushed aside the same week Jeff Dean claims they will start tying exec performance to D&I
— Rachel Thomas (@math_rachel) February 19, 2021
In 2020, Samy hired 39% women, compared to just 14% for the rest of Jeff's org 🤔 https://t.co/ydb4D4P49t
Interesting analysis by @mhmazur. Human work is driven by clear goals and is informed by task-specific context. A model that is optimized for generating plausible-sounding text, ignoring goals and context, virtually never produces any useful answer (unless by random chance). https://t.co/QPzapZgale
— François Chollet (@fchollet) February 19, 2021
Working towards herd immunity under various scenarios, using simulations, by @nprviz https://t.co/7W769CCMcQ pic.twitter.com/m9363akRJd
— Nathan Yau (@flowingdata) February 19, 2021
Ray is an open-source library for parallel and distributed Python. It can be paired with #PyTorch to rapidly scale machine learning applications. Learn more below: https://t.co/UhfPxSEoWm
— PyTorch (@PyTorch) February 19, 2021
If you're interested in GNNs for combinatorial tasks (certainly an exciting time!), we've released our 43-page comprehensive survey on the area! + detailed blueprint of algorithmic reasoning in S3.3.https://t.co/F4TG4svKMG
— Petar Veličković (@PetarV_93) February 19, 2021
with @chrsmrrs @69alodi @lyeskhalil @qcappart & Didier pic.twitter.com/P6TANTgLvr
DreamerV2, a collaboration between DeepMind, @GoogleAI and the @UofT, is the first RL agent based on a world model to achieve human-level performance on the Atari benchmark. Read more ⬇️ https://t.co/lFFuHH2Uk9
— DeepMind (@DeepMind) February 19, 2021
New in the scikit-learn main branch: a short tutorial on assessing and tuning quantile regression models with the new pinball loss metric:https://t.co/V3naQcxwz6
— Olivier Grisel (@ogrisel) February 19, 2021
before and after hyper-parameter tuning on data with asymmetric, heteroscedastic noise: pic.twitter.com/jVoPfENlxp
“I helped build ByteDance’s vast censorship machine: I wasn't proud of it, and neither were my coworkers. But that's life in today's China.” article by @shenlulushen, is worth a read if you are interested in ML ethics in production. A thread by the author:https://t.co/ivSaUwMj6L pic.twitter.com/h8MiMhtavc
— hardmaru (@hardmaru) February 19, 2021
Facebook when its platform is a driving force for genocide vs Facebook when it faces possible regulation pic.twitter.com/XrA8uHzuDY
— Max Fisher (@Max_Fisher) February 17, 2021