Ravinder Bhattoo

Civil Engineering | 🤖 Machine Learning & 🌊 Simulation

[N M Anoop Krishnan @anoopnm007]

Want to learn machine learning for materials domain or other application domains?!

Our (@haribamsuri and @RavinderBhattoo) book titled “Machine learning for materials discovery” is out! Do check it out!
https://t.co/6lDSVajrrW

Special thanks to @ProfBuehlerMIT for the preface!

[Machine Learning: Science and Technology @MLSTjournal]

'Learning the #dynamics of particle-based systems with #Lagrangian graph #neuralnetworks' by @RavinderBhattoo @SayanRanu @anoopnm007 @m3rgiitd @iitdelhi hits 500 downloads! https://t.co/GRacp6aO3L #machinelearning #statphys #compchem #graphs #AI #materials #simulation #HPC

[Machine Learning: Science and Technology @MLSTjournal]

Great new work by @RavinderBhattoo @SayanRanu @anoopnm007 @iitdelhi - 'Learning the #dynamics of particle-based systems with #Lagrangian graph #neuralnetworks' - https://t.co/GRacp6aO3L #machinelearning #statphys #compchem #graphs #AI #materials #simulation

[Pramesh CS @cspramesh]

This is a gamechanger for #STEM in India

[Notion @NotionHQ]

Introducing Notion AI 🪄 Write faster. Think bigger. Augment your creativity.

[Miles Cranmer @MilesCranmer]

Every single project on https://t.co/Ddb0fdgpUD is a programmer's dream. I'm so excited for when these go live!

[Felix Koehler @felix_m_koehler]

👩‍💻 Code along with me to build a simple forward-mode #autodiff framework ↩️ in the @JuliaLanguage using Dual Numbers and Operator Overloading:
https://t.co/J6K2FDEb4Z

[Papers with Code @paperswithcode]

🪐 Introducing Galactica. A large language model for science.

Can summarize academic literature, solve math problems, generate Wiki articles, write scientific code, annotate molecules and proteins, and more.

Explore and get weights: https://t.co/jKEP8S7Yfl

[Mastodon (@[email protected]) @joinmastodon]

Over 1 million people have joined Mastodon since October 27. Between that and those who returned to their old accounts, the number of active users has risen to over 1.6 million today, which, for context, is over 3 times what it was just about two weeks ago!

[Jitin Singla @SinglaJitin]

it's funny how people drink alcohol to just blend-in. Pathetic need to get accepted, make friends and show their progressive liberal mind.

[Kareem Carr, Ph.D. @kareem_carr]

“The floor is Microsoft Excel”

me, a data scientist: https://t.co/SFBF0cR83C

[Nature Communications @NatureComms]

Transparent peer review for all!
We will publish reviewer reports and author responses for all research articles submitted after November 1st
#OpenScience
https://t.co/9wOOv3U6y1

[Sergei Kalinin @Sergei_Imaging]

Rama Vasudevan @ramav_matsci -> APS Fellow, "For pioneering and visionary development of open-sourced physics-based machine learning methods in atomic-scale and mesoscopic imaging, and their application in physics". Congratulations, Rama!

[N M Anoop Krishnan @anoopnm007]

Wanted to know/predict the properties of all possible glasses from the periodic table? In our latest work in @Acta_Materialia, we develop ML models for predicting 25 properties of inorganic glasses with upto 225 different components covering 84 elements of the periodic table! 1/n

[N M Anoop Krishnan @anoopnm007]

Interested in a Ph.D. in AI/ML with applications to materials and robotics?

We (@SayanRanu and myself) have open positions to work on modeling the dynamics of physical systems using graph neural networks. The details of the project can be found here.
https://t.co/DgHcsRh2zW

[Thuerey Group at TUM @thuereyGroup]

We're happy to report that our paper "Guaranteed Conservation of Momentum for Learning Particle-based Fluid Dynamics" has been accepted at NeurIPS and is available now at https://t.co/AR1VwDAYws, congratulations Lukas 😀 👍

[Peter Battaglia @PeterWBattaglia]

We're hiring interns on the Structured Intelligence team at @DeepMind. If you're interested in richly structured data, representations and computations, eg., learning simulation, GNNs, probabilistic generative models, etc, please apply-

[N M Anoop Krishnan @anoopnm007]

Can GNNs be used for modeling rigid bodies and particle systems? We answer these questions in two of our latest papers accepted in NeurIPS 2022 with @SayanRanu, @RavinderBhattoo, @Bishnoi__Suresh, T Abishek and Gunjan Kumar.

[Suraj Srinivas @Suuraj]

Three papers accepted at NeurIPS'22 (!!)

1) Efficiently training low-curvature neural networks (https://t.co/nL2FpxuNKh), w/ Kyle Matoba, @hima_lakkaraju, @francoisfleuret

We propose to build NNs that are "as linear as possible", and thus eliminate excess model curvature.