🤩🤩 Very excited to share with you that I have finished working on a #Federated_Learning course. The course explains in detail several FL algorithms and their implementation step-by-step. Examples & notebooks are also available using #PyTorch#PySyft ...
https://t.co/Zmdv9jZufX
The reigning @BIGEASTWBB Player of the Week is back at it again tonight!
Take a look at Molly Mogensen's recent shot charts from our victories over Georgetown and Providence, courtesy of @ShotTracker 🏀
#GoJays x @Molly_Mogensen
My latest OpEd on why convenience always wins. And what is more convenient than the phone!!!
@Redeem_xyz - Simplifying and Accelerating the path to Web3 experiences by linking the Phone Number to Wallets and Activations.
https://t.co/EdFRwpocrS
🚨 We're doubling-down!
Thrilled to announce we're merging with @Forkast_News to power the trusted benchmarks and independent, data-driven storytelling needed by the global digital economy.
https://t.co/LNSX8oFQfX
🧵👇
New from the Twitter META team: we’re partnering with @openminedorg, a nonprofit pioneering applications of privacy-enhancing tech (PETs) and privacy-preserving machine learning (PPML), to help us be more transparent & accountable. https://t.co/I1WL9w8qCb
Do we still need SGD/Adam to train neural networks? Based on our #NeurIPS2021 paper, we are one step closer to replacing hand-designed optimizers with a single meta-model. Our meta-model can predict parameters for almost any neural network in just one forward pass. (1/n)
Super excited to share that our startup, @TripleBlindAI found by @rdasxy and Greg Storm & officially launched in November 2020, has just closed a $24m Series A investment...
More here: https://t.co/tGC2rl3J7W
We are releasing an API to turn English into code.
Make a computer game from scratch in a few minutes.
https://t.co/fv8lezNICV
btw: some people suspect that I am an AI in this video.
We’re releasing Triton 1.0, an open-source Python-like programming language for writing efficient GPU code. OpenAI researchers with no GPU programming experience have used Triton to produce kernels that are 2x faster than their PyTorch equivalents. https://t.co/bdovUjTMuF