Meta presents "ESM Metagenomic Atlas", a database of 617 million metagenomic protein structures https://actuia.com/actualite/meta-presente-esm-metagenomic-atlas-une-base-de-donnees-de-617-millions-de-structures-proteiques-metagenomiques/
… #AI #artificialintelligence
@Meta
MACHINE LEARNING
-
Meta Unveils ESM Metagenomic Atlas with 617 Million Structures
By
–
-
Iterative approach to building and refining positive datasets
By
–
from my own experience you want something interactive and change your mind around quite a bit. so you're building the positive set, seeing the results, then tweaking your positive set over time. it's an incremental iterative thing.
-
Adaptive Optimizers Should Track True Squared Gradients
By
–
Adaptive optimizers like Adam track the square of the gradient, but what they receive as the gradient is actually the sum of the gradients across the batch. It seems likely that better results at different hyper parameters could be obtained if backward passes emitted true grad^2.
-
Neural Operators and AI for Science Talk at MIT IAIFI
By
–
It was great visiting @mit @iaifi_news and give a talk about neural operators and AI for science. You can find my talk here https://
youtu.be/RR5-mYQOb7E?t=
1208
… -
Scikit-learn Algorithm Selection Cheat Sheet Guide
By
–
Scikit-learn is one of the most useful and important Python libraries for machine learning. A great cheat sheet that will help you decide which algorithm to use:
-
NVIDIA Isaac and DRIVE Sim Enable Rapid Robot and Vehicle Learning
By
–
With NVIDIA Isaac simulation technology, #robots can earn a PhD in the blink of an eye. And with NVIDIA DRIVE Sim, autonomous vehicles can drive millions of miles in a wide range of simulated scenarios so they navigate safely. Learn more: https://
nvda.ws/3xTkalW #NVIDIAstory -
Announcing redun: Open-source workflow framework for data scientists
By
–
Excited to share redun with data scientists everywhere. We hope redun will help democratize data science at scale, and support robust, reproducible science. insitro (@insitro) We're excited to announce the open sourcing of redun, an expressive, efficient, and easy-to-use workflow framework designed to deal with complex, rapidly evolving scientific workflows spanning multiple data types. Read more here: insitro.medium.com/8b06b707a… — https://nitter.net/insitro/status/1456237571340652547#m
→ View original post on X — @daphnekoller, 2021-11-04 18:32 UTC
-
insitro Announces $400M Series C Financing for Drug Discovery
By
–
A major milestone in our journey, enabled by the many accomplishments of amazing insitrocytes and support of outstanding, long-term investors. We are excited to continue towards our goal of using #ML and data at scale to bring transformative #medicines to patients. https://t.co/XRGBVFoYMR
— Daphne Koller (@DaphneKoller) 16 mars 2021A major milestone in our journey, enabled by the many accomplishments of amazing insitrocytes and support of outstanding, long-term investors. We are excited to continue towards our goal of using #ML and data at scale to bring transformative #medicines to patients. insitro (@insitro) We're thrilled to announce our $400M Series C financing, which will greatly enable us to continue advancing our vision to reshape the discovery and development of transformative medicines by leveraging #machinelearning and biology and chemistry at scale. bwnews.pr/3eL7G7v — https://nitter.net/insitro/status/1371416831840374789#m
→ View original post on X — @daphnekoller, 2021-03-16 01:54 UTC
-
Daphne Koller featured in Forbes article on ML for drug discovery
By
–
Thanks @_RobToews for including me in your @Forbes article and letting me talk about our work about our work at @insitro on using #ML for drug discovery. Honored to be included with a group of such amazing women scientists. bit.ly/3qU1DBa
→ View original post on X — @daphnekoller, 2020-12-13 23:45 UTC