5 papers
Parameter-Level Attribution of Symmetry in Trained Networks Though Parameter-Wise Functional Sensitivity
Alan Muriithi, Vedanta Thapar, Torben Berndt
When a network has learned a function with a known symmetry, can that symmetry be moved through the parametrisation---is there a motion in parameter space realising the group actio…
Machine Learning Hamiltonian Dynamical Systems with Sparse and Noisy Data
Vedanta Thapar, Abhinav Gupta
Machine learning has become a powerful tool for discovering governing laws of dynamical systems from data. However, most existing approaches degrade severely when observations are…
Embedding networks with the random walk first return time distribution
Vedanta Thapar, Renaud Lambiotte, George T. Cantwell
We propose the first return time distribution (FRTD) of a random walk as an interpretable and mathematically grounded node embedding. The FRTD assigns a probability mass function t…
Applications of Machine Learning to Modelling and Analysing Dynamical Systems
Vedanta Thapar
We explore the use of Physics Informed Neural Networks to analyse nonlinear Hamiltonian Dynamical Systems with a first integral of motion. In this work, we propose an architecture…
Examining Temporal Variation of the Fermi Coupling Constant using SNe Ia Light Curves
Akshay Rana, Vedanta Thapar, Hari Prasad S. V. +1
In standard model, the Fermi coupling constant, , sets the strength of electroweak decay. We attempt an approach to constrain the temporal variation of the Fermi coupling cons…