no code implementations • 2 Apr 2024 • Saptarshi Dasgupta, Akshat Gupta, Shreshth Tuli, Rohan Paul
This paper presents an approach that enables a robot to rapidly learn the complete 3D model of a given object for manipulation in unfamiliar orientations.
1 code implementation • 24 Feb 2024 • Harshil Vagadia, Mudit Chopra, Abhinav Barnawal, Tamajit Banerjee, Shreshth Tuli, Souvik Chakraborty, Rohan Paul
PhyPlan leverages PINNs to simulate and predict outcomes of actions in a fast and accurate manner and uses MCTS for planning.
1 code implementation • 11 Feb 2023 • Shreshth Tuli, Giuliano Casale, Nicholas R. Jennings
CILP leverages a neural network as a surrogate model to predict future workload demands with a co-simulated digital-twin of the infrastructure to compute QoS scores.
1 code implementation • 2 Dec 2022 • Shreshth Tuli, Giuliano Casale, Ludmila Cherkasova, Nicholas R. Jennings
The emergence of latency-critical AI applications has been supported by the evolution of the edge computing paradigm.
no code implementations • 16 Aug 2022 • Shreshth Tuli, Giuliano Casale, Nicholas R. Jennings
Edge Federation is a new computing paradigm that seamlessly interconnects the resources of multiple edge service providers.
no code implementations • 11 Jun 2022 • Shreshth Tuli, Matthew R. Wilkinson, Chris Kettell
We consider the specific use case of road traffic systems where incidents take the form of anomalous events, such as accidents or broken-down vehicles.
no code implementations • 23 May 2022 • Shikhar Tuli, Bhishma Dedhia, Shreshth Tuli, Niraj K. Jha
We also propose a novel NAS policy, called BOSHNAS, that leverages this new scheme, Bayesian modeling, and second-order optimization, to quickly train and use a neural surrogate model to converge to the optimal architecture.
1 code implementation • 21 May 2022 • Shreshth Tuli, Giuliano Casale, Nicholas R. Jennings
Task scheduling is a well-studied problem in the context of optimizing the Quality of Service (QoS) of cloud computing environments.
1 code implementation • 21 May 2022 • Shreshth Tuli, Giuliano Casale, Nicholas R. Jennings
This makes the problem of deploying such large-scale neural networks challenging in resource-constrained mobile edge computing platforms, specifically in mission-critical domains like surveillance and healthcare.
1 code implementation • 14 May 2022 • Shreya Sharma, Jigyasa Gupta, Shreshth Tuli, Rohan Paul, Mausam
Our goal is to enable a robot to learn how to sequence its actions to perform tasks specified as natural language instructions, given successful demonstrations from a human partner.
no code implementations • 14 Mar 2022 • Shreshth Tuli, Giuliano Casale, Nicholas R. Jennings
To address this, we present a confidence aware resilience model, CAROL, that utilizes a memory-efficient generative neural network to predict the Quality of Service (QoS) for a future state and a confidence score for each prediction.
2 code implementations • 18 Jan 2022 • Shreshth Tuli, Giuliano Casale, Nicholas R. Jennings
Efficient anomaly detection and diagnosis in multivariate time-series data is of great importance for modern industrial applications.
1 code implementation • 16 Dec 2021 • Shreshth Tuli, Giuliano Casale, Nicholas R. Jennings
Advances like deterministic surrogate models, deep neural networks (DNN) and gradient-based optimization allow low energy consumption and response times to be reached.
1 code implementation • 14 Dec 2021 • Shreshth Tuli, Giuliano Casale, Nicholas R. Jennings
Workflow scheduling is a long-studied problem in parallel and distributed computing (PDC), aiming to efficiently utilize compute resources to meet user's service requirements.
1 code implementation • 4 Dec 2021 • Shreshth Tuli, Giuliano Casale, Nicholas R. Jennings
Building a fault-tolerant edge system that can quickly react to node overloads or failures is challenging due to the unreliability of edge devices and the strict service deadlines of modern applications.
1 code implementation • 11 Oct 2021 • Shreshth Tuli, Sukhpal Singh Gill, Minxian Xu, Peter Garraghan, Rami Bahsoon, Schahram Dustdar, Rizos Sakellariou, Omer Rana, Rajkumar Buyya, Giuliano Casale, Nicholas R. Jennings
The worldwide adoption of cloud data centers (CDCs) has given rise to the ubiquitous demand for hosting application services on the cloud.
no code implementations • 6 Oct 2021 • Shreshth Tuli, Shikhar Tuli, Giuliano Casale, Nicholas R. Jennings
In standard generative deep learning models, such as autoencoders or GANs, the size of the parameter set is proportional to the complexity of the generated data distribution.
1 code implementation • 5 May 2021 • Shreshth Tuli, Rajas Bansal, Rohan Paul, Mausam
We introduce a novel neural model, termed TANGO, for predicting task-specific tool interactions, trained using demonstrations from human teachers instructing a virtual robot.
1 code implementation • 1 Sep 2020 • Shreshth Tuli, Shashikant Ilager, Kotagiri Ramamohanarao, Rajkumar Buyya
The ubiquitous adoption of Internet-of-Things (IoT) based applications has resulted in the emergence of the Fog computing paradigm, which allows seamlessly harnessing both mobile-edge and cloud resources.
1 code implementation • 9 Jun 2020 • Rajas Bansal, Shreshth Tuli, Rohan Paul, Mausam
When compared to a graph neural network baseline, it achieves 14-27% accuracy improvement for predicting known tools from new world scenes, and 44-67% improvement in generalization for novel objects not encountered during training.
Robotics
no code implementations • 6 May 2020 • Shikhar Tuli, Shreshth Tuli
Recently, the Edge Computing paradigm has gained significant popularity both in industry and academia.
2 code implementations • 3 Oct 2019 • Shreshth Tuli, Shikhar Tuli, Udit Jain, Rajkumar Buyya
We demonstrate the effectiveness of APEX through a case study of overwriting surveillance videos by CryPy malware on Raspberry-Pi based Edge deployment and show 678% and 32% higher recovery than Ext4 and current state-of-the-art File Systems.
Operating Systems
2 code implementations • 29 Nov 2018 • Shreshth Tuli, Redowan Mahmud, Shikhar Tuli, Rajkumar Buyya
The requirement of supporting both latency sensitive and computing intensive Internet of Things (IoT) applications is consistently boosting the necessity for integrating Edge, Fog and Cloud infrastructure.
Distributed, Parallel, and Cluster Computing