🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Tapson's Rules of Machine Learning: 4. Time spent on data cleaning is an order of magnitude more productive than time spent on hyperparameter tuning. (Extreme example: achieved a Top 10 result in Kaggle using linear regression, as the only team that cleaned 50/60Hz noise first.)

Should be a fun crowd > We've got an exciting #chemistry and #artificialintelligence event lined up for April 25 in San Francisco. Hope you can come! #machinelearning #datascience #deeplearning American Chemical Society bit.ly/2OdAXIk

Two School scientists recently showed how to train computers to think more like scientists. #MachineLearning Keiser Lab UC San Francisco tiny.ucsf.edu/iZsMOj

Great community discussion on #AI & #Chemistry last night, hosted by CALACS & #NovartisBiome. Question from the audience - if you had all the resources and $$ to do it, what would you prioritize to move the field fwd?

Neat read of CZI Science team's takeaways on building a network of scientific investigators that's more than the sum of its parts. I've really appreciated their commitment to iteration & design thinking in putting these meetings together

This year's "Advanced Topics in #DeepLearning for Biological Sciences (BMI 219)" course starts Monday morning! Looking forward to Dr. Nobuyuki Ota's third year of cutting-edge #ML lectures - #UCSF buff.ly/2HlJIx0

Want to try your own #DeepLearning models for #AlzheimersDisease pathologies? Ziqi Tang's paper, code, AND data are open to everyone - let us know what you discover! bit.ly/tangAI4AD - This has been a fantastic collab w Prof Dugger UC Davis.

Looking forward to moderating our #UCaiBIO panel on #Responsible Use of AI in Biomedicine” 6/18 with Keiser Lab Christine Borgman @LaurelRiek !

LOVE the systemwide #AI collaborations already happening within the University of California! nature.com/articles/s4146… #UCaiBio

We actually hit 2400/hr -- about two annotations per standard human breath!

If a #datascientist is a scientist, shouldn't they also be a #databreaker?

A #redteam finds fragility in our security models. A scientific #AIredteam would find where our #machinelearning models, #databias, and assumptions are just as fragile. #reproducibility

Wow, I'm so impressed by University of Michigan undergrad Yannah Melle, who just gave an awesome talk on her summer research in the Keiser Lab as part of the UCSF Summer Research Training Program! Great job and thanks so much for making the lab awesome, can't wait to see what you do next!

Congrats to kangway chuang, who joins the 2019 class of Arnold O. Beckman Postdoctoral Fellows in Chemical Sciences! Thank you Beckman Foundation for the game-changing support & recognition of an exceptional scientist.

Ian Holmes CZI Science Chan Zuckerberg Biohub Network @Facebook Please submit your signature here: forms.gle/XMrxZsT5PQa78L… we will update the letter on a rolling basis as more CZI-funded scientists sign

Today, over 140 scientists funded by CZI are urging Facebook to implement stricter moderation rules. As a CZI staffer who’s proud of the work we’re doing, I wholeheartedly support this call for policies to curb posts that incite violence against US citizens and racial hatred.

As a lab funded by the awesome CZI Science, we stand with our colleagues in an open letter to Mark Zuckerberg asking @Facebook to enforce its own policies on misinformation and incendiary statements in this critical time

Accuracy is not sufficient for using image analysis AI support tools in clinic. Our latest work by Albert Young in npj Journals with the Wei Lab (buff.ly/2Ypua4v) describes how computational "stress tests" help ensure AI models are clinic ready: buff.ly/3c6tPLZ

Congrats to the Vevo Therapeutics team on joining the #AWSGenAIAccelerator cohort! Excited to support their groundbreaking work in #GenerativeAI, single-cell foundation models, & million-cell screens opening frontiers in drug design. Accelerator info: go.aws/45lDsQh

🧬🔮 Single cell foundation models have been a recent hot topic in bio-ML! A few of the recent methods and some thoughts 🧬🔮 1) Geneformer 2) scGPT 3) scFoundation 4) Exceiver