检索结果-内蒙古大学图书馆

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Sinhababu, Nilanjan Parry, Andrew Ganguly, Debasis Samanta, Debasis Mitra, Pabitra Centre for Computational and Data Sciences IIT Kharagpur India School of Computing Science University of Glasgow United Kingdom Department of Computer Science and Engineering IIT Kharagpur India

ISBN: (纸本)9798891761681

A supervised ranking model, despite its effectiveness over traditional approaches, usually involves complex processing - typically multiple stages of task-specific pre-training and fine-tuning. This has motivated researchers to explore simpler pipelines leveraging large language models (LLMs) that can work in a zero-shot manner. However, since zero-shot inference does not make use of a training set of pairs of queries and their relevant documents, its performance is mostly worse than that of supervised models, which are trained on such example pairs. Motivated by the existing findings that training examples generally improve zero-shot performance, in our work, we explore if this also applies to ranking models. More specifically, given a query and a pair of documents, the preference prediction task is improved by augmenting examples of preferences for similar queries from a training set. Our proposed pairwise few-shot ranker demonstrates consistent improvements over the zero-shot baseline on both in-domain (TREC DL) and out-domain (BEIR subset) retrieval benchmarks. Our method also achieves a close performance to that of a supervised model without requiring any complex training pipeline. © 2024 Association for computational Linguistics.

关键词： computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Secured and Privacy-Preserving GPU-Based Machine Learning Inference in Trusted Execution Environment: A Comprehensive Survey 17

Secured and Privacy-Preserving GPU-Based Machine Learning In...

引用

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Chaudhuri, Arunava Shukla, Shubhi Bhattacharya, Sarani Mukhopadhyay, Debdeep Indian Institute of Technology Kharagpur Department of Computer Science and Engineering Kharagpur India Indian Institute of Technology Kharagpur Centre for Computational and Data Sciences Kharagpur India

ISBN: (纸本)9798331531195

With the rapid advancement of machine learning (ML) models and their widespread application across various sectors such as intrusion detection, medical diagnosis, natural language processing, and autonomous driving, these technologies have achieved remarkable success. However, this progress has also raised significant concerns about ensuring the security of ML models and protecting both private training data and model outputs from getting exposed in a shared cloud environment. To address these challenges, researchers have proposed various methodologies to create privacy-preserving, secure, and trustworthy model execution environments to prevent adversarial attacks. This study provides a comprehensive review of Trusted Execution Environment (TEE) implementations across different hardware accelerators. It also offers an overview of modern techniques for preserving privacy and security in execution environments, while identifying critical research gaps that require attention. In essence, this survey is an important resource for researchers, providing insights into recent methodologies and guiding them to focus on pressing research challenges. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Minimal Counters, Maximum Insight: Simplifying System Performance With HPC Clusters for Optimized Monitoring

IEEE Computer Architecture Letters

引用

IEEE Computer Architecture Letters 2025年第1期24卷 177-180页

作者： Shukla, Shubhi Singh, Abhijeet Chakraborty, Rajdeep Chakraborty, Anirban Rathod, Tejas Mumbaikar, Harshal Munigala, Manoj Kumar Madhusudhan, K.N. Mitra, Pabitra Mukhopadhyay, Debdeep Indian Institute of Technology Kharagpur Centre for Computational Data Sciences India Indian Institute of Technology Kharagpur Computer Science and Engineering Department India Intel Corporation Bangalore India

As computer systems become more complex, evaluating performance requires tracking various hardware performance counters that capture the system's internal activities. While these counters provide valuable insights, their growing number makes it challenging to identify the most relevant ones for performance analysis. In this paper, we investigate the correlation between performance counter values and overall system performance, while also exploring the inter-correlation between different counters. Our findings demonstrate that specific counters are strongly correlated with key performance metrics and that significant redundancy exists among counters. By leveraging these relationships, we propose a method for selecting a small, representative set of performance counters. This streamlined set can further be used to accurately predict performance score across various workloads and system configurations. © 2002-2011 IEEE.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Smoothed-LSTM: Advancing spatio-temporal NDVI prediction in semi-automated dataset for rice crop

Smoothed-LSTM: Advancing spatio-temporal NDVI prediction in ...

引用

2024 International Conference on Machine Intelligence for GeoAnalytics and Remote Sensing, MIGARS 2024

作者： Dey, Anamika Sarkar, Somrita Kumar, Debajyoti Mondal, Arijit Mitra, Pabitra Indian Institute of Technology Kharagpur Centre For Computational And Data Sciences Kharagpur India Indian Institute of Technology Department of Computer Science And Engineering Patna Bihta India Indian Institute of Technology Kharagpur Department of Computer Science And Engineering Kharagpur India

ISBN: (纸本)9798350389678

Accurate Normalized Difference Vegetation Index (NDVI) forecasting is crucial for effective agricultural planning. However, a good prediction of the same requires sufficient data, but structured data is not available in the public domain or open-source community. Also, most of the existing methods do not consider spatial information. This study presents a novel semi-automated dataset generation framework that utilizes Sentinel-2, POWER data Access Viewer, and Google Earth Engine to create a comprehensive time-series dataset. We propose a smoothed long short-term memory (LSTM) model considering time series, historical meteorological, and spatial information. The proposed Smoothed-LSTM-based model outperforms Traditional-LSTM models, demonstrating its effectiveness in NDVI prediction for agricultural applications. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Spatio-Temporal NDVI Prediction for Rice Crop

引用

SN Computer science 2025年第3期6卷 1-13页

作者： Dey, Anamika Sarkar, Somrita Mondal, Arijit Mitra, Pabitra Centre for Computational and Data Sciences Indian Institute of Technology Kharagpur West Bengal Kharagpur 721302 India Department of Computer Science and Engineering Indian Institute of Technology Patna Bihar Bihta 801106 India Department of Computer Science and Engineering Indian Institute of Technology Kharagpur West Bengal Kharagpur 721302 India

Accurately predicting the Normalized Difference Vegetation Index (NDVI) is crucial for effective agricultural planning and decision-making. Despite much literature on NDVI prediction, most of these methods do not consider spatial-temporal variations. Generating a dataset for predicting NDVI is another major bottleneck, as such data needs to be collected over an extensive period. In this work, we develop a semi-automated framework to generate a comprehensive time-series dataset after necessary preprocessing using the information from Sentinel-2, POWER data Access Viewer, and the Google Earth Engine (GEE). We propose a deep learning-based model to predict NDVI based on its historical time series and meteorological and spatial information for the rice crop in India. Here, we use a Long Short-Term Memory (LSTM)-based model augmented with spatial information to predict the NDVI of the near-about region for which the data is unavailable. We compared the proposed approach with a method that uses a weighted average of nearest neighbors prediction. Also, we compare the proposed method with existing statistical techniques such as the Autoregressive (AR), AutoRegressive Integrated Moving Average (ARIMA), and Seasonal AutoRegressive Integrated Moving Average (SARIMA). Experimental results show that our methodology outperforms other techniques by a margin of 4% to 8%. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Autoregressive integrated moving average Long short-term memory Normalized difference vegetation index Seasonal autoregressive integrated moving average Sentinel-2 Weighted average of nearest neighbors prediction

来源：评论

学校读者我要写书评

暂无评论

Ordinary Differential Equation Identification Based on Sparse Bayesian Learning and Collaborative Neurodynamic Optimization 6

Ordinary Differential Equation Identification Based on Spars...

引用

6th International Conference on Communication, Image and Signal Processings, CCISP 2021

作者： Okunev, Alexey Burnaev, Evgeny Wang, Jun Center for Computational and Data-Intensive Science and Engineering Skoltech Moscow Russia

ISBN: (纸本)9781665432795

Sparse Bayesian learning based on collaborative neurodynamic optimization (CNO-SBL) is a novel neural network approach proposed recently for sparse regression. In this paper, we demonstrate how well CNO-SBL performs for ordinary differential equation identification. It is shown that the approach is capable of recovering ordinary differential equations and outperforms the sequentially thresholded least square (STLS) algorithm in terms of accuracy for small size of dictionaries. © 2021 IEEE.

关键词： Ordinary differential equations

来源：评论

学校读者我要写书评

暂无评论

Guardian of the Ensembles: Introducing Pairwise Adversarially Robust Loss for Resisting Adversarial Attacks in DNN Ensembles

Guardian of the Ensembles: Introducing Pairwise Adversariall...

引用

2025 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025

作者： Shukla, Shubhi Dalui, Subhadeep Alam, Manaar Datta, Shubhajit Mondal, Arijit Mukhopadhyay, Debdeep Chakrabarti, Partha Pratim Centre for Computational and Data Sciences Iit Kharagpur India Iit Kharagpur Computer Science and Engineering Department India Center for Cyber Security New York University Abu Dhabi United Arab Emirates Iit Kharagpur Department of Artificial Intelligence India Iit Patna Computer Science and Engineering Department India

ISBN: (纸本)9798331510831

Adversarial attacks rely on transferability, where an adversarial example (AE) crafted on a surrogate classifier tends to mislead a target classifier. Recent ensemble methods demonstrate that AEs are less likely to mislead multiple classifiers in an ensemble. This paper proposes a new ensemble training using a Pairwise Adversarially Robust Loss (PARL) that by construction produces an ensemble of classifiers with diverse decision boundaries. PARL utilizes outputs and gradients of each layer with respect to network parameters in every classifier within the ensemble simultaneously. PARL is demonstrated to achieve higher robustness against black-box transfer attacks than previous ensemble methods as well as adversarial training without adversely affecting clean example accuracy. Extensive experiments using standard Resnet20, WideResnet28-10 classifiers demonstrate the robustness of PARL against state-of-the-art adversarial attacks. While maintaining similar clean accuracy and lesser training time, the proposed architecture has a 24.8% increase in robust accuracy (= 0.07) from the state-of-the art method. Code is available at: https://***/shubhishukla10/PARL © 2025 IEEE.

关键词： adversarial attack decision-boundary diversity defense ensemble models

来源：评论

学校读者我要写书评

暂无评论

Crop Yield Prediction Using Multimodal Meta-Transformer and Temporal Graph Neural Networks

IEEE Transactions on AgriFood Electronics

引用

IEEE Transactions on AgriFood Electronics 2024年第2期2卷 545-553页

作者： Sarkar, Somrita Dey, Anamika Pradhan, Ritam Sarkar, Upendra Mohan Chatterjee, Chandranath Mondal, Arijit Mitra, Pabitra Indian Institute of Technology Kharagpur Centre for Computational and Data Sciences Kharagpur721302 India Indian Institute of Technology Kharagpur Department of Industrial and Systems Engineering Kharagpur721302 India Indian Institute of Technology Kharagpur Department of Agricultural and Food Engineering Kharagpur721302 India Indian Institute of Technology Patna Department of Computer Science and Engineering Patna801106 India Indian Institute of Technology Kharagpur Department of Computer Science and Engineering Kharagpur721302 India

Crop yield prediction is a crucial task in agricultural science, involving the classification of potential yield into various levels. This is vital for both farmers and policymakers. The features considered for this task are diverse, including weather, soil, and historical yield data. Recently, plant images captured in different modalities, such as red-green-blue, infrared, and multispectral bands, have also been utilized. Most of these data are inherently temporal. Integrating such multimodal and temporal data is advantageous for yield classification. In this work, a deep learning framework based on meta-transformers and temporal graph neural networks has been proposed to achieve this goal. Meta-Transformers allow the modeling of multimodal interactions, while temporayel graph neural networks enable the utilization of time sequences. Experimental results on the publicly available EPFL multimodal dataset demonstrate that the proposed framework achieves a high classification accuracy of nearly 97%, surpassing other state-of-the-art models, such as long short-term memory networks, 1-D convolutional neural networks, and Transformers. In addition, the proposed model excels in accuracy metrics, with a precision of approximately 98%, an F1-Score of 91%, and a recall of 94% in crop yield prediction. © 2024 IEEE.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

A novel myocarditis detection combining deep reinforcement learning and an improved differential evolution algorithm

引用

CAAI Transactions on Intelligence Technology 2024年第6期9卷 1347-1360页

作者： Jing Yang Touseef Sadiq Jiale Xiong Muhammad Awais Uzair Aslam Bhatti Roohallah Alizadehsani Juan Manuel Gorriz Department of Computer System and Technology Faculty of Computer Science and Information TechnologyUniversiti MalayaKuala LumpurMalaysia Centre for Artificial Intelligence Research(CAIR) Department of Information and Communication TechnologyUniversity of AgderGrimstadNorway Department of Creative Technologies Air UniversityIslamabadPakistan School of Information and Communication Engineering Hainan UniversityHaikouHainanChina Institute for Intelligent Systems Research and Innovation(IISRI) Deakin UniversityWaurn PondsVictoriaAustralia Data Science and Computational Intelligence Institute University of GranadaGranadaSpain

Myocarditis is a serious cardiovascular ailment that can lead to severe consequences if not promptly *** is triggered by viral infections and presents symptoms such as chest pain and heart *** detection is crucial for successful treatment,and cardiac magnetic resonance imaging(CMR)is a valuable tool for identifying this ***,the detection of myocarditis using CMR images can be challenging due to low contrast,variable noise,and the presence of multiple high CMR slices per *** overcome these challenges,the approach proposed incorporates advanced techniques such as convolutional neural networks(CNNs),an improved differential evolution(DE)algorithm for pre-training,and a reinforcement learning(RL)-based model for *** this method presented a significant challenge due to the imbalanced classification of the Z-Alizadeh Sani myocarditis dataset from Omid Hospital in *** address this,the training process is framed as a sequential decision-making process,where the agent receives higher rewards/penalties for correctly/incorrectly classifying the minority/majority ***,the authors suggest an enhanced DE algorithm to initiate the backpropagation(BP)process,overcoming the initialisation sensitivity issue of gradient-based methods like back-propagation during the training *** effectiveness of the proposed model in diagnosing myocarditis is demonstrated through experimental results based on standard performance ***,this method shows promise in expediting the triage of CMR images for automatic screening,facilitating early detection and successful treatment of myocarditis.

关键词： classification differential evolution myocarditis reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Few-shot Prompting for Pairwise Ranking: An Effective Non-Parametric Retrieval Model

arXiv

引用

arXiv 2024年

A supervised ranking model, despite its advantage of being effective, usually involves complex processing - typically multiple stages of task-specific pre-training and fine-tuning. This has motivated researchers to explore simpler pipelines leveraging large language models (LLMs) that are capable of working in a zero-shot manner. However, since zero-shot inference does not make use of a training set of pairs of queries and their relevant documents, its performance is mostly worse than that of supervised models, which are trained on such example pairs. Motivated by the existing findings that training examples generally improve zero-shot performance, in our work, we explore if this also applies to ranking models. More specifically, given a query and a pair of documents, the preference prediction task is improved by augmenting examples of preferences for similar queries from a training set. Our proposed pairwise few-shot ranker demonstrates consistent improvements over the zero-shot baseline on both in-domain (TREC DL) and out-domain (BEIR subset) retrieval benchmarks. Our method also achieves a close performance to that of a supervised model without requiring any complex training pipeline. © 2024, CC BY.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：