Building Human-Machine Trust via Interpretability
نویسندگان
چکیده
منابع مشابه
Trust Building via Risk Taking:
The role of risk taking in building trust relations has largely been overlooked in the burgeoning literature on trust in the social sciences, yet it is central to understanding how trust develops. We argue that a series of risk taking behaviors is indispensable to building a trust relation. Experiments were conducted in Japan and the United States to examine the independent and cross-cultural e...
متن کاملInterpretability via Model Extraction
e ability to interpret machine learning models has become increasingly important now that machine learning is used to inform consequential decisions. We propose an approach called model extraction for interpreting complex, blackbox models. Our approach approximates the complex model using a much more interpretable model; as long as the approximation quality is good, then statistical properties...
متن کاملBuilding Trust Between Patients and Physicians
Repairing and enhancing patient wellbeing are considered the most significant goals in the health sector. It is observed that a trustful relationship between physicians and other medical team members on one side and the patients and their families on the other side is really important to achieve the fundamental purposes in the “Art of Medicine”....
متن کاملBuilding Trust Between Patients and Physicians
Repairing and enhancing patient wellbeing are considered the most significant goals in the health sector. It is observed that a trustful relationship between physicians and other medical team members on one side and the patients and their families on the other side is really important to achieve the fundamental purposes in the “Art of Medicine”....
متن کاملMachine Agency in Human-Machine Networks; Impacts and Trust Implications
We live in an emerging hyper-connected era in which people are in contact and interacting with an increasing number of other people and devices. Increasingly, modern IT systems form networks of humans and machines that interact with one another. As machines take a more active role in such networks, they exert an increasing level of influence on other participants. We review the existing literat...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the AAAI Conference on Artificial Intelligence
سال: 2019
ISSN: 2374-3468,2159-5399
DOI: 10.1609/aaai.v33i01.33019919