It was a pleasure to talk to Prateek Joshi about AI+Science and increase awareness around this important area!

x.com/animaanandkuma…

📢 Fourth keynote reveal for #ClimateInformatics 2024:
Prof. Anima Anandkumar!

📅 22–24 April BMA House + online, hosted by the The Alan Turing Institute.

🎟️ Registration closing 17 April or when capacity is reached.

🔗 bit.ly/49qRKR8

How does neural operators relate to neural radiance fields (NeRF)? Neural operators are a generalization of NeRFs: from representing a single function to learning operators. Neural operators are conditional neural fields, conditioned on different input functions. Our neural…

Neural operators are extensions of neural networks to handle continuous inputs and outputs (function spaces) and hence, accurately represent solutions to PDEs. But how do they relate to numerical solver for PDEs?
Figure below shows the pseudo-spectral solver is a special case of…

The advantage of neural operators over neural networks (e.g. UNet or transformer) is in the ability to capture finer scales than the observed data resolution. In left figure below, the prediction at higher wave number (resolution) is where neural networks (NN) suffer if…

The class of neural operators contain all neural networks. Neural networks fix resolution or dimension of input and outputs before learning the mapping, while in neural operators we do not have this restriction.
In figure, you can see this difference: neural networks assumes…

Our Nature review Nature Reviews Physics on neural operator. It explains the prospect of deep learning on advancing science, simulation, and design. A new exciting era of progress w many new exciting challenges for us, ML/AI +domain researchers. nature
nature.com/articles/s4225…

Like many others, I came to US as an immigrant and made it my home. I benefitted immensely by being around smart and passionate people everywhere I went. Finding a path for capturing the value of immigrants we train here is really important to keep us competitive and innovative.

After years of work, we can now move on from GP regression to universal functional regression.

OpFlow: Just do GP regression, without Gaussian prior assumption. Learn prior from your data. 🔥🔥

arxiv.org/pdf/2404.02986…

Jw, Yaozhong Shi, Angela Gao, Zachary Ross
Caltech NVIDIA

It’s been an absolute pleasure to work with Prof. Anima Anandkumar and Zongyi Li at Caltech on this one. We do an extensive analysis of how FNOs can help model Magnetohydrodynamics, often found within Tokamak plasmas.

Our recent work titled “Plasma surrogate modelling using Fourier Neural Operators” 👇

#NuclearFusion #PlasmaModeling #FNO #FourierNeuralOperators #Tokamak #MHD #PlasmaDynamics #PredictiveModeling #RealTimeMonitoring #MASTTokamak #RenewableEnergy #SustainableFuture #UKAEA

AI with Fourier Neural Operators speeds up Plasma modeling in Nuclear fusion by a million times
Predicting plasma evolution within a Tokamak reactor is crucial to realizing the goal of sustainable fusion. A big challenge are disruptions that occur when the plasma gets unstable…

Excited to announce the AI for Math Workshop at #ICML2024 ICML Conference! Join us for groundbreaking discussions on the intersection of AI and mathematics. 🤖🧮

📅 Workshop details: sites.google.com/view/ai4mathwo…

📜 Submit your pioneering work: sites.google.com/view/ai4mathwo…

🏆 Take on our…

It was lovely to meet 古賀大貴/Hiroki Koga and fellow TED Talks speakers, and the highly inspiring Chris Anderson and the TED Talks crew. I came away energized and with many new ideas to improve my talk.
古賀大貴/Hiroki Koga strawberries and tomatoes are other worldly and highly addictive! It is hard to…