Zobrazeno 1 - 10
of 755
pro vyhledávání: '"Tan, Gang"'
This paper investigates neuron dropout as a post-processing bias mitigation for deep neural networks (DNNs). Neural-driven software solutions are increasingly applied in socially critical domains with significant fairness implications. While neural n
Externí odkaz:
http://arxiv.org/abs/2407.04268
Data-driven software solutions have significantly been used in critical domains with significant socio-economic, legal, and ethical implications. The rapid adoptions of data-driven solutions, however, pose major threats to the trustworthiness of auto
Externí odkaz:
http://arxiv.org/abs/2407.01423
Pseudocode in a scholarly paper provides a concise way to express the algorithms implemented therein. Pseudocode can also be thought of as an intermediary representation that helps bridge the gap between programming languages and natural languages. H
Externí odkaz:
http://arxiv.org/abs/2406.04635
Autor:
Jia, Xiaodong, Tan, Gang
Accurate description of program inputs remains a critical challenge in the field of programming languages. Active learning, as a well-established field, achieves exact learning for regular languages. We offer an innovative grammar inference tool, V-S
Externí odkaz:
http://arxiv.org/abs/2404.04201
Heap memory errors remain a major source of software vulnerabilities. Existing memory safety defenses aim at protecting all objects, resulting in high performance cost and incomplete protection. Instead, we propose an approach that accurately identif
Externí odkaz:
http://arxiv.org/abs/2310.06397
This thesis explores open-sourced machine learning (ML) model explanation tools to understand whether these tools can allow a layman to visualize, understand, and suggest intuitive remedies to unfairness in ML-based decision-support systems. Machine
Externí odkaz:
http://arxiv.org/abs/2307.05029
File formats specify how data is encoded for persistent storage. They cannot be formalized as context-free grammars since their specifications include context-sensitive patterns such as the random access pattern and the type-length-value pattern. We
Externí odkaz:
http://arxiv.org/abs/2304.04859
The deep feedforward neural networks (DNNs) are increasingly deployed in socioeconomic critical decision support software systems. DNNs are exceptionally good at finding minimal, sufficient statistical patterns within their training data. Consequentl
Externí odkaz:
http://arxiv.org/abs/2304.04199
Publikováno v:
Jichu yixue yu linchuang, Vol 44, Iss 4, Pp 572-576 (2024)
Objective Using our team's recent research achievement “the cervical ultrasound scanning route map” as a teaching tool, to evaluate its impact on the learning effectiveness and confidence of beginners in the process of learning cervical spinal ul
Externí odkaz:
https://doaj.org/article/974d148fbef047f88b5fb6d65ff3d98a
Autor:
Beugin, Yohan, Burke, Quinn, Hoak, Blaine, Sheatsley, Ryan, Pauley, Eric, Tan, Gang, Hussain, Syed Rafiul, McDaniel, Patrick
Millions of consumers depend on smart camera systems to remotely monitor their homes and businesses. However, the architecture and design of popular commercial systems require users to relinquish control of their data to untrusted third parties, such
Externí odkaz:
http://arxiv.org/abs/2208.09776