Highlights: Microsoft and MIT researchers have developed a new AI assessment model. The model can identify instances where autonomous systems have learnt from exceptions in training examples. The study has been presented in a couple of papers. A new model developed by researchers at Microsoft and MIT is capable of identifying instances where autonomous systems have learnt from training examples that don't match with what's actually happening, reports MIT News. It seems this model could be used in the future to improve the safety factor in artificial intelligence systems like driverless vehicles and autonomous robots. Researchers from the two organisations have presented their findings in a couple of papers that will be presented at the upcoming Association for the Advancement of Artificial Intelligence conference. "The model helps autonomous systems better know what they don’t know," says co-author Ramya Ramakrishnan, a graduate student in the Computer Science and Artificial Intelligence Laboratory. "Many times, when these systems are deployed, their trained simulations don’t match the real-world setting [and] they could make mistakes, such as getting into accidents. The idea is to use humans to bridge that gap between simulation and the real world, in a safe way, so we can reduce some of those errors." The approach used by the researchers first puts an AI system through simulation training, where the system creates a "policy" that maps every situation to the best actions it can take. The system is then made to work in the real world, where humans give error signals in areas where the system's actions are forbidden. Humans are allowed to provide signals to the system in more than one way, namely "corrections" and "demonstrations". For example, a driver behind the wheel of an autonomously driving car could force inputs in certain driving situations to tell the system that it was not acting unacceptably in those situations. The system then records which situation-and-action pairs were accepatable and unacceptable. According to Ramakrishnan, the next step is compiling the information to ask, "How likely am I to make a mistake in this situation where I received these mixed signals?" If the system learns that it is right to give way to an ambulance from a simulation in which way was given to an ambulance nine out of ten times, human inputs that block the ambulance will be treated as actions that are "right". In short, exceptions like blocking the way of a speeding ambulance could confuse, or worse, corrupt the system. "When the system is deployed into the real world, it can use this learned model to act more cautiously and intelligently. If the learned model predicts a state to be a blind spot with high probability, the system can query a human for the acceptable action, allowing for safer execution," adds Ramakrishnan. The pair of papers that will be presented at the upcoming Association for the Advancement of Artificial Intelligence conference was originally presented at last year's Autonomous Agents and Multiagent Systems conference. Related Read: Windows 7 support to end in a year, Microsoft says
from Latest Technology News http://bit.ly/2RS7tFa
flipkart
Subscribe to:
Post Comments (Atom)
flipkart
Edit videos on your mobile phone using the YouTube Create App
YouTube has introduced its new mobile app called ‘YouTube Create’. This app offers an easy way for creators to edit their videos right from ...
- September 2023 (83)
- August 2023 (126)
- July 2023 (113)
- June 2023 (102)
- May 2023 (162)
- April 2023 (160)
- March 2023 (148)
- February 2023 (136)
- January 2023 (173)
- December 2022 (163)
- November 2022 (163)
- October 2022 (181)
- September 2022 (178)
- August 2022 (174)
- July 2022 (136)
- June 2022 (125)
- May 2022 (146)
- April 2022 (130)
- March 2022 (143)
- February 2022 (132)
- January 2022 (145)
- December 2021 (157)
- November 2021 (239)
- October 2021 (269)
- September 2021 (270)
- August 2021 (212)
- July 2021 (252)
- June 2021 (225)
- May 2021 (184)
- April 2021 (181)
- March 2021 (343)
- February 2021 (299)
- January 2021 (320)
- December 2020 (334)
- November 2020 (305)
- October 2020 (318)
- September 2020 (340)
- August 2020 (347)
- July 2020 (337)
- June 2020 (310)
- May 2020 (308)
- April 2020 (418)
- March 2020 (316)
- February 2020 (282)
- January 2020 (329)
- December 2019 (323)
- November 2019 (393)
- October 2019 (403)
- September 2019 (386)
- August 2019 (454)
- July 2019 (579)
- June 2019 (509)
- May 2019 (697)
- April 2019 (725)
- March 2019 (746)
- February 2019 (702)
- January 2019 (932)
- December 2018 (758)
- November 2018 (729)
- October 2018 (835)
- September 2018 (838)
- August 2018 (548)
- March 2018 (24)
-
Now that the first Developer Preview of the next version of Android has gone live, we can expect to see more and more reports of upcoming fe...
-
Huawei, it seems, cannot seem to steer away from controversy around its smartphones’ camera capabilities. This time, a Chinese photographer ...
-
OnePlus could be on the road to launch its first smartwatch very soon. A report recently surfaced that reveals a listing on Indonesia's ...
No comments:
Post a Comment