Why Am I Stuck? Token-Level Causal Reasoning for AI and Robotics

author: Denver Dash, Intel Science and Technology Center (ISTC), Carnegie Mellon University
published: Oct. 6, 2014,   recorded: December 2013,   views: 1625

Related Open Educational Resources

Related content

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Lecture popularity: You need to login to cast your vote.


Much of the research in causality in the past 20 years has focused on statistical modeling of systems: i.e., understanding cause and effect on entire populations of entities where large datasets can be employed to learn causal relations. This work has made great progress and has been essential in enabling programs to reason about cause and effect in scenarios which would otherwise be hard for humans due to their complexity or due to uncertainty that exists over large populations. However, another important use for causal reasoning exists and has been understudied in AI, namely, reasoning about cause-and-effect in single streams of events, or “token-level” causality.

Link this page

Would you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !

Write your own review or comment:

make sure you have javascript enabled or clear this field: