Trustworthy machine learningFault diagnosis is efficient to improve the safety, reliability, and cost-effectiveness of industrial machinery. Deep learning has been extensively investigated in fault diagnosis, exhibiting state-of-the-art performance. However, since deep learning is inherently uninterpretable,...
practice, since most real-world data are easily imperfect and corrupted. Therefore, in this talk, I will introduce our recent works on trustworthy machine learning from a theoretical view of robust optimization, including the reliability on noisy labels and the robustness against adversarial examples....
The goal of the workshop, fifth in the series at COMPSAC, is to foster interaction and information exchange among AI researchers and practitioners, both from academia and industry, on the safe, reliable and trustworthy application of Artificial intelligence (AI) and Machine learning (ML) in real...
AI development norms should be reshaped, incentives aligned, and ethics integrated throughout the machine learning process, which requires close collaboration across technology, ethics, law, policy, and other fields. Our review contributes a robust framework to assess trust in LLMs and analyzes the ...
The statistical and black-box nature of state-of-the-art machine learning models makes them untrustworthy, raising ethical concerns and limiting their practical utility. Furthermore, the evaluation of autograding is typically confined to small, monolingual datasets for a specific question type. This ...
This effect can be associated with some factors captured in the development indicators for access to information technology infrastructure and highlights the importance of trustworthy and reliable data for measuring existing biases in globally deployed ML solutions. While we have presented here a case ...
(Henesey et al.2020). Perhaps, blockchain technology could resolve data security and render this novice digital technology more trustworthy for individuals in the shipping industry (Yánez et al.2020). Additionally, storing collected data represents one more challenge for shipping companies (Dai et ...
Secondly, industry stakeholders such as network operators, network equipment vendors, solution developers, etc., shall come together to establish protocols and define clear ToU for the proprietary network data to encourage trustworthy data sharing. On the other hand, for preserving data privacy, ML ...
(van der Bles et al.2020). Especially engagement with people who distrust researchers, can be an opportunity to make policies more trust-promoting. While researchers should be trustworthy, the research subject as truster also has a responsibility, namely to be understanding and receptive to trust-...
(Henesey et al.2020). Perhaps, blockchain technology could resolve data security and render this novice digital technology more trustworthy for individuals in the shipping industry (Yánez et al.2020). Additionally, storing collected data represents one more challenge for shipping companies (Dai et ...