There's a new opening on our team at the @mlcolab, working to bring #MachineLearning to the sciences.

One of the things I love about our mission is how diverse the work is. From one day to the next we might be teaching a workshop, consulting a scientist on an exciting research project, building a probabilistic model to fit a dataset, or writing #FOSS software.

For more information, see https://fediscience.org/@mlcolab/109953546334327601

#SciML #ML4Science

#NewPaper on Factorized Fourier Neural Operators accepted to ICLR 2023.

Neural Operators approximately solve differential equations, using deep learning to fit the mapping (an operator), avoiding discretization. The Fourier Neural Operator models the (Fourier transformed) spectrum of the dynamical system. Our idea (called F-FNO) is more than factorizing each dimension separately, and works on various dynamical systems, topologies, and meshes. https://openreview.net/forum?id=tmIiMPl4IPa
#MachineLearning #ml4science

This paper models "discovery" as being interested in finding things with high label values, have a big set of things to label, and can only label a few of the things once each. Similar to scientific discovery. The setting is more general than #bandits, and uses #ExperimentalDesign type ideas. The paper considers the ratio of expected instant regret to information gain as a rule for selecting the next item to label.
https://arxiv.org/abs/2205.14829
#MachineLearning #ml4science

What are the best written theses you've ever read? #ml4science #genomics #machinelearning

Missed our workshop?

Don't worry! ✨

The recording is released on Youtube.

Each talk has its own video, and everything is in a convenient playlist.

It will live here:
https://www.youtube.com/watch?list=PLib5UZJfdkBBQXiJc0rHeH76jgxtqpsid

(The videos release tomorrow)

#MachineLearning #DeepLearning #DataScience #Data #MLOps #Software #Pydata #Python #Tech #Career #Science #ML4Science #ML #AI #Reproducibility #Testing

How do we avoid the worst mistakes in machine learning?!

Got 2 hours?

We created a workshop for you at PyData Global this Friday!

🌟 We put in the work and created:
• Awesome talks
• Project Jupyter notebooks
• Good discussions and chats

Share this with your #MachineLearning colleagues, enthusiasts and especially #PhD students!

See you Friday, December 2nd at 13:00 UTC.

#Deeplearning #ML #AI #Tech #Career #ML4Science #Python

Machine Learning in the real world is hard!

So, let's make the hard things easier in just 2 hours!

𝙍𝙚𝙖𝙡-𝙬𝙤𝙧𝙡𝙙 𝙋𝙚𝙧𝙨𝙥𝙚𝙘𝙩𝙞𝙫𝙚𝙨 𝙩𝙤 𝘼𝙫𝙤𝙞𝙙 𝙩𝙝𝙚 𝙒𝙤𝙧𝙨𝙩 𝙈𝙞𝙨𝙩𝙖𝙠𝙚𝙨 𝙪𝙨𝙞𝙣𝙜 𝙈𝙖𝙘𝙝𝙞𝙣𝙚 𝙇𝙚𝙖𝙧𝙣𝙞𝙣𝙜 𝙞𝙣 𝙎𝙘𝙞𝙚𝙣𝙘𝙚

Join the workshop this Friday at 13:00 UTC!

Please share this with your fellow #MachineLearning enthusiasts, researchers, scientists and, of course, #PhD candidates!

https://realworld-ml.xyz

#DeepLearning #DataScience #Python #Reproducibility #tech #career #MLOps #ml #ai #Science #ML4Science

Moving to a smaller instance. A re-#introduction.

I research #MachineLearning for Scientific Discovery. #ml4science #ai4science
I advocate for #OpenSource and #OpenScience when possible. A lot of my effort goes to solving problems in #LifeScience #Genomics and #RadioAstronomy.

Read our book on Mathematics for Machine Learning at https://mml-book.com

I cook to relax.

Reposting #introduction

I'm a scientist working on #quantumcomputing at Quantinuum. I oversee our R&D collaborations and research in combining quantum algorithms and #machinelearning techniques. My main interests are #Bayesian and probabilistic approaches to #ML, #statistics, #GenerativeModels, #inference, #ml4science. In the past I was a researcher in #ultracoldatoms and #boseeinsteincondensates, and I enjoy #literature.

I hope we can grow a welcoming #quantum community on Mastodon.

Hello Fediverse! We are the ML ⇌ Science Colaboratory, part of the #ML4Science
cluster at @unituebingen. We are working to accelerate scientific discovery with #MachineLearning through workshops, consultations, and cooperations with scientists.

To learn more about us, see our website! https://mlcolab.org

As our members appear on Mastodon, we'll introduce them in the replies.

#SciML #science #introduction

Time for an #introduction.

I'm a scientist working on #quantumcomputing at Quantinuum. I oversee our R&D collaborations and research in combining quantum algorithms and #machinelearning techniques. My main interests are #Bayesian and probabilistic approaches to #ML, #statistics, #GenerativeModels, #inference, #ml4science. In the past I was a researcher in #ultracoldatoms and #boseeinsteincondensates, and I enjoy #literature.

I hope we can grow a welcoming #quantum community on Mastodon.

Are you a scientist applying Machine Learning?

I wrote a tutorial with ready-to-use notebooks to make your life easier!

Let's focus on 3 aspects:
• More Citations
• Easier Review
• Better Collaboration

☝ First things first!

This was a #EuroScipy2022 tutorial.

In the future, there will be a talk recording. Until then, the gist:

1. Model Evaluation
2. Benchmarking
3. Model Sharing
4. Testing
5. Interpretability
6. Ablation

https://github.com/JesperDramsch/euroscipy-2022-ml-for-science-reproducibility-tutorial

🧵👇

#machinelearning #science #ml4science

Conformal prediction is a practical way to estimate uncertainty. This paper uses it to manage covariate shift when designing new proteins.
https://www.pnas.org/doi/10.1073/pnas.2204569119

#ml4science #MachineLearning

#introduction I research #ml4science and care about #opensource. Read our book for free at https://mml-book.com.

I cook to relax.