中文
相关论文

相关论文: Data-Driven AI Model Signal-Awareness Enhancement …

200 篇论文

The expanding role of Artificial Intelligence (AI) in diverse engineering domains highlights the challenges associated with deploying AI models in new operational environments, involving substantial investments in data collection and model…

人工智能 · 计算机科学 2024-05-14 Daryl Mupupuni , Anupama Guntu , Liang Hong , Kamrul Hasan , Leehyun Keel

The expanding role of Artificial Intelligence (AI) in diverse engineering domains highlights the challenges associated with deploying AI models in new operational environments, involving substantial investments in data collection and model…

计算机视觉与模式识别 · 计算机科学 2024-03-22 Daryl Mupupuni , Anupama Guntu , Liang Hong , Kamrul Hasan , Leehyun Keel

Understanding specifically where a model focuses on within an image is critical for human interpretability of the decision-making process. Deep learning-based solutions are prone to learning coincidental correlations in training datasets,…

计算机视觉与模式识别 · 计算机科学 2024-10-22 Aidan Boyd , Mohamed Trabelsi , Huseyin Uzunalioglu , Dan Kushnir

Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…

机器学习 · 计算机科学 2024-08-12 Pietro Morerio , Ruggero Ragonesi , Vittorio Murino

Structured prediction is often approached by training a locally normalized model with maximum likelihood and decoding approximately with beam search. This approach leads to mismatches as, during training, the model is not exposed to its…

计算与语言 · 计算机科学 2020-10-13 Renato Negrinho , Matthew R. Gormley , Geoffrey J. Gordon

Large language models make remarkable progress in reasoning capabilities. Existing works focus mainly on deductive reasoning tasks (e.g., code and math), while another type of reasoning mode that better aligns with human learning, inductive…

计算与语言 · 计算机科学 2025-03-18 Kedi Chen , Zhikai Lei , Fan Zhang , Yinqi Zhang , Qin Chen , Jie Zhou , Liang He , Qipeng Guo , Kai Chen , Wei Zhang

Materials discovery is a cornerstone of modern technological advancement, yet it remains constrained by traditional trial-and-error paradigms and the inherent bias of human intuition. Artificial intelligence (AI) has emerged as a…

Deep Learning (DL) applications are being used to solve problems in critical domains (e.g., autonomous driving or medical diagnosis systems). Thus, developers need to debug their systems to ensure that the expected behavior is delivered.…

软件工程 · 计算机科学 2023-07-19 Mohammad Wardat , Breno Dantas Cruz , Wei Le , Hridesh Rajan

Recent years have seen the successful application of deep learning to software engineering (SE). In particular, the development and use of pre-trained models of source code has enabled state-of-the-art results to be achieved on a wide…

软件工程 · 计算机科学 2022-05-25 Changan Niu , Chuanyi Li , Bin Luo , Vincent Ng

The wide use of machine learning is fundamentally changing the software development paradigm (a.k.a. Software 2.0) where data becomes a first-class citizen, on par with code. As machine learning is used in sensitive applications, it becomes…

数据库 · 计算机科学 2019-04-25 Ki Hyun Tae , Yuji Roh , Young Hun Oh , Hyunsu Kim , Steven Euijong Whang

With the great success of pre-trained models, the pretrain-then-finetune paradigm has been widely adopted on downstream tasks for source code understanding. However, compared to costly training a large-scale model from scratch, how to…

软件工程 · 计算机科学 2022-03-16 Deze Wang , Zhouyang Jia , Shanshan Li , Yue Yu , Yun Xiong , Wei Dong , Xiangke Liao

AI-based solutions demonstrate remarkable results in identifying vulnerabilities in software, but research has consistently found that this performance does not generalize to unseen codebases. In this paper, we specifically investigate the…

密码学与安全 · 计算机科学 2025-10-08 Rijha Safdar , Danyail Mateen , Syed Taha Ali , M. Umer Ashfaq , Wajahat Hussain

Artificial Intelligence (AI) or Machine Learning (ML) systems have been widely adopted as value propositions by companies in all industries in order to create or extend the services and products they offer. However, developing AI/ML systems…

软件工程 · 计算机科学 2020-11-10 Elizamary Nascimento , Anh Nguyen-Duc , Ingrid Sundbø , Tayana Conte

The advent of large language models (LLMs) has significantly advanced artificial intelligence (AI) in software engineering (SE), with source code embeddings playing a crucial role in tasks such as source code clone detection and source code…

软件工程 · 计算机科学 2025-06-04 Zixiang Xian , Chenhui Cui , Rubing Huang , Chunrong Fang , Zhenyu Chen

In recent years, the rise of deep learning and automation requirements in the software industry has elevated Intelligent Software Engineering to new heights. The number of approaches and applications in code understanding is growing, with…

软件工程 · 计算机科学 2022-05-04 Ruoting Wu , Yuxin Zhang , Qibiao Peng , Liang Chen , Zibin Zheng

Deep learning (DL) techniques have achieved significant success in various software engineering tasks (e.g., code completion by Copilot). However, DL systems are prone to bugs from many sources, including training data. Existing literature…

软件工程 · 计算机科学 2025-08-12 Mehil B Shah , Mohammad Masudur Rahman , Foutse Khomh

Recent studies have demonstrated remarkable advancements in source code learning, which applies deep neural networks (DNNs) to tackle various software engineering tasks. Similar to other DNN-based domains, source code learning also requires…

软件工程 · 计算机科学 2025-02-07 Zeming Dong , Qiang Hu , Yuejun Guo , Zhenya Zhang , Maxime Cordy , Mike Papadakis , Yves Le Traon , Jianjun Zhao

The discussion around AI-Engineering, that is, Software Engineering (SE) for AI-enabled Systems, cannot ignore a crucial class of software systems that are increasingly becoming AI-enhanced: Those used to enable or support the SE process,…

软件工程 · 计算机科学 2026-01-28 Himon Thakur , Armin Moin

Autoregressive Sequence-To-Sequence models are the foundation of many Deep Learning achievements in major research fields such as Vision and Natural Language Processing. Despite that, they still present significant limitations. For…

计算与语言 · 计算机科学 2024-08-27 Jia Cheng Hu , Roberto Cavicchioli , Alessandro Capotondi

This paper presents a hybrid methodology that enhances the training process of deep learning (DL) models by embedding domain expert knowledge using ontologies and answer set programming (ASP). By integrating these symbolic AI methods, we…

人工智能 · 计算机科学 2025-06-10 Fadi Al Machot , Martin Thomas Horsch , Habib Ullah