Zobrazeno 1 - 10
of 2 250
pro vyhledávání: '"Babu, A. Ramesh"'
Autor:
Naug, Avisek, Guillen, Antonio, Luna, Ricardo, Gundecha, Vineet, Rengarajan, Desik, Ghorbanpour, Sahand, Mousavi, Sajad, Babu, Ashwin Ramesh, Markovikj, Dejan, Kashyap, Lekhapriya D, Sarkar, Soumyendu
Machine learning has driven an exponential increase in computational demand, leading to massive data centers that consume significant amounts of energy and contribute to climate change. This makes sustainable data center control a priority. In this p
Externí odkaz:
http://arxiv.org/abs/2408.07841
Autor:
Naug, Avisek, Guillen, Antonio, Gutierrez, Ricardo Luna, Gundecha, Vineet, Ghorbanpour, Sahand, Mousavi, Sajad, Babu, Ashwin Ramesh, Sarkar, Soumyendu
There have been growing discussions on estimating and subsequently reducing the operational carbon footprint of enterprise data centers. The design and intelligent control for data centers have an important impact on data center carbon footprint. In
Externí odkaz:
http://arxiv.org/abs/2404.12498
Autor:
Sarkar, Soumyendu, Naug, Avisek, Guillen, Antonio, Luna, Ricardo, Gundecha, Vineet, Babu, Ashwin Ramesh, Mousavi, Sajad
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 20, pp. 22322-22330, Mar. 2024
The rapid growth of machine learning (ML) has led to an increased demand for computational power, resulting in larger data centers (DCs) and higher energy consumption. To address this issue and reduce carbon emissions, intelligent design and control
Externí odkaz:
http://arxiv.org/abs/2404.10786
Autor:
Sarkar, Soumyendu, Gundecha, Vineet, Ghorbanpour, Sahand, Shmakov, Alexander, Babu, Ashwin Ramesh, Naug, Avisek, Pichard, Alexandre, Cocho, Mathieu
Publikováno v:
IJCAI 2023, Proceedings of the Thirty-Second International Joint Conference on Artificial IntelligenceAugust 2023, Article No 688, Pages 6201 to 6209
The industrial multi-generator Wave Energy Converters (WEC) must handle multiple simultaneous waves coming from different directions called spread waves. These complex devices in challenging circumstances need controllers with multiple objectives of
Externí odkaz:
http://arxiv.org/abs/2404.10991
Autor:
Sarkar, Soumyendu, Babu, Ashwin Ramesh, Mousavi, Sajad, Gundecha, Vineet, Naug, Avisek, Ghorbanpour, Sahand
Publikováno v:
2024 Proceedings of the AAAI Conference on Artificial Intelligence
We present a generic Reinforcement Learning (RL) framework optimized for crafting adversarial attacks on different model types spanning from ECG signal analysis (1D), image classification (2D), and video classification (3D). The framework focuses on
Externí odkaz:
http://arxiv.org/abs/2403.18985
Autor:
Sarkar, Soumyendu, Naug, Avisek, Luna, Ricardo, Guillen, Antonio, Gundecha, Vineet, Ghorbanpour, Sahand, Mousavi, Sajad, Markovikj, Dejan, Babu, Ashwin Ramesh
Publikováno v:
2024 Proceedings of the AAAI Conference on Artificial Intelligence
As machine learning workloads significantly increase energy consumption, sustainable data centers with low carbon emissions are becoming a top priority for governments and corporations worldwide. This requires a paradigm shift in optimizing power con
Externí odkaz:
http://arxiv.org/abs/2403.14092
Autor:
Mousavi, Sajad, Gutiérrez, Ricardo Luna, Rengarajan, Desik, Gundecha, Vineet, Babu, Ashwin Ramesh, Naug, Avisek, Guillen, Antonio, Sarkar, Soumyendu
Publikováno v:
NeurIPS 2023 Workshop on Robustness of Few-shot and Zero-shot Learning in Foundation Models 2023(NeurIPS 2023)
We propose a self-correction mechanism for Large Language Models (LLMs) to mitigate issues such as toxicity and fact hallucination. This method involves refining model outputs through an ensemble of critics and the model's own feedback. Drawing inspi
Externí odkaz:
http://arxiv.org/abs/2310.18679
Autor:
Sarkar, Soumyendu, Babu, Ashwin Ramesh, Mousavi, Sajad, Carmichael, Zachariah, Gundecha, Vineet, Ghorbanpour, Sahand, Luna, Ricardo, Guillen, Gutierrez Antonio, Naug, Avisek
We present a novel framework for generating adversarial benchmarks to evaluate the robustness of image classification models. Our framework allows users to customize the types of distortions to be optimally applied to images, which helps address the
Externí odkaz:
http://arxiv.org/abs/2310.18626
Autor:
Shmakov, Alexander, Naug, Avisek, Gundecha, Vineet, Ghorbanpour, Sahand, Gutierrez, Ricardo Luna, Babu, Ashwin Ramesh, Guillen, Antonio, Sarkar, Soumyendu
Bayesian Optimization (BO), guided by Gaussian process (GP) surrogates, has proven to be an invaluable technique for efficient, high-dimensional, black-box optimization, a critical problem inherent to many applications such as industrial design and s
Externí odkaz:
http://arxiv.org/abs/2310.03912
Autor:
Naug, Avisek, Guillen, Antonio, Gutiérrez, Ricardo Luna, Gundecha, Vineet, Markovikj, Dejan, Kashyap, Lekhapriya Dheeraj, Krause, Lorenz, Ghorbanpour, Sahand, Mousavi, Sajad, Babu, Ashwin Ramesh, Sarkar, Soumyendu
Publikováno v:
2023 BuildSys '23: Proceedings of the 10th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation
The increasing global emphasis on sustainability and reducing carbon emissions is pushing governments and corporations to rethink their approach to data center design and operation. Given their high energy consumption and exponentially large computat
Externí odkaz:
http://arxiv.org/abs/2310.03906