Ashwin Ramesh Babu
YOU?
Author Swipe
View article: DCcluster-Opt: Benchmarking Dynamic Multi-Objective Optimization for Geo-Distributed Data Center Workloads
DCcluster-Opt: Benchmarking Dynamic Multi-Objective Optimization for Geo-Distributed Data Center Workloads Open
The increasing energy demands and carbon footprint of large-scale AI require intelligent workload management in globally distributed data centers. Yet progress is limited by the absence of benchmarks that realistically capture the interpla…
View article: LC-Opt: Benchmarking Reinforcement Learning and Agentic AI for End-to-End Liquid Cooling Optimization in Data Centers
LC-Opt: Benchmarking Reinforcement Learning and Agentic AI for End-to-End Liquid Cooling Optimization in Data Centers Open
Liquid cooling is critical for thermal management in high-density data centers with the rising AI workloads. However, machine learning-based controllers are essential to unlock greater energy efficiency and reliability, promoting sustainab…
View article: Robustness Evaluation for Video Models with Reinforcement Learning
Robustness Evaluation for Video Models with Reinforcement Learning Open
Evaluating the robustness of Video classification models is very challenging, specifically when compared to image-based models. With their increased temporal dimension, there is a significant increase in complexity and computational cost. …
View article: Hierarchical Multi-Agent Framework for Carbon-Efficient Liquid-Cooled Data Center Clusters
Hierarchical Multi-Agent Framework for Carbon-Efficient Liquid-Cooled Data Center Clusters Open
Reducing the environmental impact of cloud computing requires efficient workload distribution across geographically dispersed Data Center Clusters (DCCs) and simultaneously optimizing liquid and air (HVAC) cooling with time shift of worklo…
View article: Reinforcement Learning Platform for Adversarial Black-box Attacks with Custom Distortion Filters
Reinforcement Learning Platform for Adversarial Black-box Attacks with Custom Distortion Filters Open
We present a Reinforcement Learning Platform for Adversarial Black-box untargeted and targeted attacks, RLAB, that allows users to select from various distortion filters to create adversarial examples. The platform uses a Reinforcement Lea…
View article: Hierarchical Multi-Agent Framework for Carbon-Efficient Liquid-Cooled Data Center Clusters
Hierarchical Multi-Agent Framework for Carbon-Efficient Liquid-Cooled Data Center Clusters Open
Reducing the environmental impact of cloud computing requires efficient workload distribution across geographically dispersed Data Center Clusters (DCCs) and simultaneously optimizing liquid and air (HVAC) cooling with time shift of worklo…
View article: Reinforcement Learning Platform for Adversarial Black-box Attacks with Custom Distortion Filters
Reinforcement Learning Platform for Adversarial Black-box Attacks with Custom Distortion Filters Open
We present a Reinforcement Learning Platform for Adversarial Black-box untargeted and targeted attacks, RLAB, that allows users to select from various distortion filters to create adversarial examples. The platform uses a Reinforcement Lea…
View article: SustainDC: Benchmarking for Sustainable Data Center Control
SustainDC: Benchmarking for Sustainable Data Center Control Open
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…
View article: A Configurable Pythonic Data Center Model for Sustainable Cooling and ML Integration
A Configurable Pythonic Data Center Model for Sustainable Cooling and ML Integration Open
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 foo…
View article: Carbon Footprint Reduction for Sustainable Data Centers in Real-Time
Carbon Footprint Reduction for Sustainable Data Centers in Real-Time Open
As machine learning workloads are significantly increasing 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 opt…
View article: Sustainability of Data Center Digital Twins with Reinforcement Learning
Sustainability of Data Center Digital Twins with Reinforcement Learning Open
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 a…
View article: Robustness and Visual Explanation for Black Box Image, Video, and ECG Signal Classification with Reinforcement Learning
Robustness and Visual Explanation for Black Box Image, Video, and ECG Signal Classification with Reinforcement Learning Open
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 …
View article: Carbon Footprint Reduction for Sustainable Data Centers in Real-Time
Carbon Footprint Reduction for Sustainable Data Centers in Real-Time Open
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 optimizin…
View article: PyDCM: Custom Data Center Models with Reinforcement Learning for Sustainability
PyDCM: Custom Data Center Models with Reinforcement Learning for Sustainability Open
The increasing global emphasis on sustainability and reducing carbon\nemissions is pushing governments and corporations to rethink their approach to\ndata center design and operation. Given their high energy consumption and\nexponentially …
View article: N-Critics: Self-Refinement of Large Language Models with Ensemble of Critics
N-Critics: Self-Refinement of Large Language Models with Ensemble of Critics Open
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. Dr…
View article: Detecting Cognitive Fatigue in Subjects with Traumatic Brain Injury from FMRI Scans Using Self-Supervised Learning
Detecting Cognitive Fatigue in Subjects with Traumatic Brain Injury from FMRI Scans Using Self-Supervised Learning Open
Understanding cognitive states from fMRI data have yet to be investigated to its full extent due to its complex nature. In this work, the problem of understanding cognitive fatigue among TBI patients has been formulated as a multi-class cl…
View article: Data from "Benchmark Generation Framework with Customizable Distortions for Image Classifier Robustness"
Data from "Benchmark Generation Framework with Customizable Distortions for Image Classifier Robustness" Open
This repository contains the data from the paper, "Benchmark Generation Framework with Customizable Distortions for Image Classifier Robustness." Relevant URLs: https://hewlettpackard.github.io/trust-ml/ https://github.com/HewlettPackard/t…
View article: Data from "Benchmark Generation Framework with Customizable Distortions for Image Classifier Robustness"
Data from "Benchmark Generation Framework with Customizable Distortions for Image Classifier Robustness" Open
This repository contains the data from the paper, "Benchmark Generation Framework with Customizable Distortions for Image Classifier Robustness." Relevant URLs: https://hewlettpackard.github.io/trust-ml/ https://github.com/HewlettPackard/t…
View article: Skip Training for Multi-Agent Reinforcement Learning Controller for Industrial Wave Energy Converters
Skip Training for Multi-Agent Reinforcement Learning Controller for Industrial Wave Energy Converters Open
Recent Wave Energy Converters (WEC) are equipped with multiple legs and generators to maximize energy generation. Traditional controllers have shown limitations to capture complex wave patterns and the controllers must efficiently maximize…
View article: Self-Supervised Human Activity Representation for Embodied Cognition Assessment
Self-Supervised Human Activity Representation for Embodied Cognition Assessment Open
Physical activities, according to the embodied cognition theory, are an important manifestation of cognitive functions. As a result, in this paper, the Activate Test of Embodied Cognition (ATEC) system is proposed to assess various cogniti…
View article: Manifolk: A 3D t-SNE Visualizer
Manifolk: A 3D t-SNE Visualizer Open
Manifolk is a tool to visualize the output of dimensionality reduction algorithms like t-SNE, PCA etc. One of this tool's main uses is that it de-clutters graphs by plotting data points pertaining to a subset of labels. The subset of label…
View article: Understanding Cognitive Fatigue from fMRI Scans with Self-supervised Learning
Understanding Cognitive Fatigue from fMRI Scans with Self-supervised Learning Open
Functional magnetic resonance imaging (fMRI) is a neuroimaging technique that records neural activations in the brain by capturing the blood oxygen level in different regions based on the task performed by a subject. Given fMRI data, the p…
View article: A Survey of Robots in Healthcare
A Survey of Robots in Healthcare Open
In recent years, with the current advancements in Robotics and Artificial Intelligence (AI), robots have the potential to support the field of healthcare. Robotic systems are often introduced in the care of the elderly, children, and perso…
View article: A Survey on Contrastive Self-Supervised Learning
A Survey on Contrastive Self-Supervised Learning Open
Self-supervised learning has gained popularity because of its ability to avoid the cost of annotating large-scale datasets. It is capable of adopting self-defined pseudolabels as supervision and use the learned representations for several …
View article: A Survey on Contrastive Self-Supervised Learning
A Survey on Contrastive Self-Supervised Learning Open
Self-supervised learning has gained popularity because of its ability to avoid the cost of annotating large-scale datasets. It is capable of adopting self-defined pseudolabels as supervision and use the learned representations for several …
View article: An automated assessment system for embodied cognition in children
An automated assessment system for embodied cognition in children Open
We present our preliminary data analysis towards an automated assessment system for the Activate Test for Embodied Cognition (ATEC), a test which measures cognitive skills through physical activity. More specifically, we present two core A…
View article: Towards Deep Learning based Hand Keypoints Detection for Rapid Sequential Movements from RGB Images
Towards Deep Learning based Hand Keypoints Detection for Rapid Sequential Movements from RGB Images Open
Hand keypoints detection and pose estimation has numerous applications in computer vision, but it is still an unsolved problem in many aspects. An application of hand keypoints detection is in performing cognitive assessments of a subject …
View article: Towards Deep Learning based Hand Keypoints Detection for Rapid\n Sequential Movements from RGB Images
Towards Deep Learning based Hand Keypoints Detection for Rapid\n Sequential Movements from RGB Images Open
Hand keypoints detection and pose estimation has numerous applications in\ncomputer vision, but it is still an unsolved problem in many aspects. An\napplication of hand keypoints detection is in performing cognitive assessments\nof a subje…