Steps Toward Robust Artificial Intelligence - Thomas G Dietterich, Oregon State University
Offered By: Alan Turing Institute via YouTube
Course Description
Overview
Syllabus
Intro
STEPS TOWARD ROBUST ARTIFICIAL INTELLIGENCE
Marvin Minsky (1927-2016)
Minsky: Difference between Computer Programs and People
Outline
Self-Driving Cars
Automated Surgical Assistants
Autonomous Weapons
Conclusion
Robustness Lessons from Biology
Decision Making under Uncertainty
Robustness to Downside Risk
Robust Optimization • Many Al reasoning problems can be formulated as optimization problems
Impose a Budget on the Adversary
Detect Surprises
Monitor Auxiliary Regularities
Monitor Auxiliary Tasks
Open Category Object Recognition
Prediction with Anomaly Detection
Theoretical Guarantee
Related Efforts
Use a Bigger Model The risk of Unknown Unknowns may be reduced if we model more aspects of the world • Knowledge Base Construction Information Extraction & Knowledge Base Population
Use Causal Models
Employ a Portfolio of Models
Portfolio Methods in SAT & CSP
Summary
Taught by
Alan Turing Institute
Related Courses
Artificial IntelligenceMassachusetts Institute of Technology via MIT OpenCourseWare Bayesian Networks 2 - Forward-Backward - Stanford CS221: AI
Stanford University via YouTube Bayesian Networks 1 - Inference - Stanford CS221: AI
Stanford University via YouTube AI & ML in Cyber Security - Why Algorithms Are Dangerous
Black Hat via YouTube Probabilistic Scripts for Automating Common-Sense Tasks
Strange Loop Conference via YouTube