15 citations · 63 across the 15 of their papers we have counts for
5 papers · 1 filter
Learning Compositional Structures for Deep Learning: Why Routing-by-agreement is Necessary
Sai Raam Venkatraman, Ankit Anand, S. Balasubramanian +1
A formal description of the compositionality of neural networks is associated directly with the formal grammar-structure of the objects it seeks to represent. This formal grammar-s…
Self-supporting wormholes with massive vector field
Ankit Anand, Prasanta K. Tripathy
In this paper we consider a massive vector field in the background of a space-time obtained by certain Z2 quotient of the BTZ black hole. We analyse the back reaction of the matter…
Learning to Prove from Synthetic Theorems
Eser Aygün, Zafarali Ahmed, Ankit Anand +5
A major challenge in applying machine learning to automated theorem proving is the scarcity of training data, which is a key ingredient in training successful deep learning models.…
Collisional time and shear relaxation time for interacting QGP
Ankit Anand, Souvik Paul, Sarthak Satapathy +1
We have studied the collisional time and relaxation time of a QGP(Quark-Gluon Plasma) by parameterizing them by temperature. From this parameterization we have obtained the decay r…
Mapping QGP interaction through its temperature dependent degeneracy factor
Ranjesh Kumar, Ankit Anand, Souvik Paul +2
We have parameterized the degeneracy factor in terms of temperature and using this we have tried to compare and study the LQCD(Lattice Quantum Chromodynamics) data with our data.