most citedRandomness and signal propagation in physics-informed neural networks (PINNs): A neural PDE perspective

1 citations · 1 across the 4 of their papers we have counts for

collaborators

8 papers

cs.LG2026

Deep Neural Networks as Discrete Dynamical Systems: Implications for Physics-Informed Learning

Abhisek Ganguly, Santosh Ansumali, Sauro Succi

We revisit the analogy between feed-forward deep neural networks (DNNs) and discrete dynamical systems derived from neural integral equations and their corresponding partial differ…

physics.plasm-ph2026

Magnetohydrodynamic equilibrium and neutronics study on MAST-U using Jenga framework

Saptarshi Rajan Sarkar, Rahul Babu Koneru, Ravi Gupta +4

Tokamak design is inherently challenging due to several cross-competing effects which require a careful and calibrated treatment to obtain an optimal operational envelope. Incorpor…

physics.flu-dyn2026

Fluid-kinetic multiscale solver for wall-bounded turbulence

Akshay Chandran, Praveen Kumar Kolluru, Berni J. Alder +2

We present a two-level (fluid-kinetic) coupling procedure for the simulation of wall-bounded flows at Reynolds numbers up to thousands. The method combines a kinetic Direct Simulat…

cs.LG20261 cited

Randomness and signal propagation in physics-informed neural networks (PINNs): A neural PDE perspective

Jean-Michel Tucny, Abhisek Ganguly, Santosh Ansumali +1

Physics-informed neural networks (PINNs) often exhibit weight matrices that appear statistically random after training, yet their implications for signal propagation and stability…

physics.plasm-ph2026

Design and mechanical analysis of the PRAGYA tokamak vacuum vessel

Ravi Gupta, Rahul Babu Koneru, Saptarshi Rajan Sarkar +4

PRAGYA is India's first privately developed low aspect ratio tokamak designed by Pranos Fusion Energy. The device is designed for a plasma major radius (R0) of about 0.4 m, a plasm…

math.NA2026

Kinetic-based regularization: Learning spatial derivatives and PDE applications

Abhisek Ganguly, Santosh Ansumali, Sauro Succi

Accurate estimation of spatial derivatives from discrete and noisy data is central to scientific machine learning and numerical solutions of PDEs. We extend kinetic-based regulariz…