2021年春季斯坦福大学推出了《可信机器学习》课程 CS 329T: Trustworthy Machine Learning Stanford, Spring 2021 CS 329T | Syllabusweb.stanford.edu/class/cs329t/syllabus.html 本课程将提供最先进的机器学习方法的介绍,旨在使人工智能更值得信赖。 本课程关注四个概念: 可解释、公平性、隐私性和鲁棒性。我们首...
研究方向: • 可信机器学习:数据隐私保护,可解释性,对抗机器学习,公平性,真实性,可复性,可靠性 • 机器学习理论:大规模数据优化,高维统计,强化学习,量子机器学习 ICML/NeurIPS/ICLR、CVPR/ICCV/ECCV、ACL…
课题组专场嘉宾及内容简介:韩波老师,Assistant Professor,Introduction of Trustworthy Machine Learning and Reasoning (TMLR) Group 田洪端,Ph.D. Student,Mind the gap between prototypes and images in cross-domain finetuning 朱嘉宁,Ph.D. Student,What If the Input is Expanded in OOD Detection? 王启舟,...
课程介绍 In an era where machine learning models are integrated into critical decision-making processes,ensuring their reliability, resilience and ethical adherence is paramount. The Trustworthy Machine Learningshort course will provide an introducti...
Trustworthy Machine Learning (the entire book)pdfpaperbackslides Front Matter and Prefacepdfhtml Part 1: Introduction and Preliminaries Chapter 1: Establishing Trustpdfhtml Chapter 2: Machine Learning Lifecyclepdfhtml Chapter 3: Safetypdfhtml Part 2: Data ...
As machine learning technology gets applied to actual products and solutions, new challenges have emerged. Models unexpectedly fail to generalize to small changes in the distribution, tend to be confident on novel data they have never seen, or cannot communicate the rationale behind their decisions ...
Balancing Transparency and Risk: An Overview of the Security and Privacy Risks of Open-Source Machine Learning Models Chapter © 2025 The Need of Trustworthy Artificial Intelligence Chapter © 2024 Toward Responsible Artificial Intelligence Systems: Safety and Trustworthiness Chapter © 2024 Expl...
Add a description, image, and links to the trustworthy-machine-learning topic page so that developers can more easily learn about it. Curate this topic Add this topic to your repo To associate your repository with the trustworthy-machine-learning topic, visit your repo's landing page and ...
In recent years, machine learning techniques have been utilized in sensitive areas such as health, medical diagnosis, facial recognition, cybersecurity, etc. With this exponential growth comes potential large-scale ethical, safety, and social ramifications. With this enhanced ubiquity and sensitivity, ...
During the past decade, deep learning has achieved great success in healthcare. However, most existing methods aim at model performance in terms of higher accuracy, which lacks the information reflecting the reliability of the prediction. It cannot be trustworthy for diagnosis making and even is ...