Zobrazeno 1 - 10
of 83
pro vyhledávání: '"Kumar, Swagat"'
Autor:
Kumar, Swagat, Wilmott, Colin Michael
The Schrodinger equation describes how quantum states evolve according to the Hamiltonian of the system. For physical systems, we have it that the Hamiltonian must be a Hermitian operator to ensure unitary dynamics. For anti-Hermitian Hamiltonians, t
Externí odkaz:
http://arxiv.org/abs/2407.01147
Autor:
Kumar, Swagat, Wilmott, Colin Michael
Publikováno v:
Sci Rep 14, 20156 (2024)
The quantum imaginary time evolution (QITE) methodology was developed to overcome a critical issue as regards non-unitarity in the implementation of imaginary time evolution on a quantum computer. QITE has since been used to approximate ground states
Externí odkaz:
http://arxiv.org/abs/2405.01313
This paper addresses the problem of visual feature representation learning with an aim to improve the performance of end-to-end reinforcement learning (RL) models. Specifically, a novel architecture is proposed that uses a heterogeneous loss function
Externí odkaz:
http://arxiv.org/abs/2301.13473
This paper presents a benchmarking study of some of the state-of-the-art reinforcement learning algorithms used for solving two simulated vision-based robotics problems. The algorithms considered in this study include soft actor-critic (SAC), proxima
Externí odkaz:
http://arxiv.org/abs/2201.04224
Autor:
Kumar, Swagat
This paper provides the details of implementing two important policy gradient methods to solve the inverted pendulum problem. These are namely the Deep Deterministic Policy Gradient (DDPG) and the Proximal Policy Optimization (PPO) algorithm. The pro
Externí odkaz:
http://arxiv.org/abs/2105.07998
Publikováno v:
IEEE Transaction on Affective Computing 2020
Affect is often expressed via non-verbal body language such as actions/gestures, which are vital indicators for human behaviors. Recent studies on recognition of fine-grained actions/gestures in monocular images have mainly focused on modeling spatia
Externí odkaz:
http://arxiv.org/abs/2101.06634
This paper presents a robotic system (\textit{Chitrakar}) which autonomously converts any image of a human face to a recognizable non-self-intersecting loop (Jordan Curve) and draws it on any planar surface. The image is processed using Mask R-CNN fo
Externí odkaz:
http://arxiv.org/abs/2011.10781
This paper looks into the problem of handling imbalanced data in a multi-label classification problem. The problem is solved by proposing two novel methods that primarily exploit the geometric relationship between the feature vectors. The first one i
Externí odkaz:
http://arxiv.org/abs/2010.05155
In this paper, we look into the problem of estimating per-pixel depth maps from unconstrained RGB monocular night-time images which is a difficult task that has not been addressed adequately in the literature. The state-of-the-art day-time depth esti
Externí odkaz:
http://arxiv.org/abs/2010.01402
Autor:
Verma, Richa, Singhal, Aniruddha, Khadilkar, Harshad, Basumatary, Ansuma, Nayak, Siddharth, Singh, Harsh Vardhan, Kumar, Swagat, Sinha, Rajesh
We propose a Deep Reinforcement Learning (Deep RL) algorithm for solving the online 3D bin packing problem for an arbitrary number of bins and any bin size. The focus is on producing decisions that can be physically implemented by a robotic loading a
Externí odkaz:
http://arxiv.org/abs/2007.00463