Running Programs in Reverse for Deeper A.I.
Offered By: Strange Loop Conference via YouTube
Course Description
Overview
Explore the concept of inverse simulation and its applications in artificial intelligence and human cognition in this thought-provoking conference talk from Strange Loop. Delve into how running programs in reverse from output to input can solve complex problems in vision, planning, and inference. Learn about ReverseFlow, a tool that combines deep learning and parametric inversion to compile a program's source code into its inverse. Discover how this approach offers practical solutions for understanding and replicating human cognitive processes, such as reconstructing 3D structures from 2D images and predicting safe street-crossing behavior. Gain insights from MIT Ph.D. candidate Zenna Tavares on building computer programs that emulate human thinking, covering topics like mental simulation, mental animation, and philosophical implications of this innovative approach to AI development.
Syllabus
Introduction
Mental simulation
Mental animation
Philosophy
Approach
Functional Version
Julia
Conclusion
Questions
Taught by
Strange Loop Conference
Tags
Related Courses
Neural Networks for Machine LearningUniversity of Toronto via Coursera 機器學習技法 (Machine Learning Techniques)
National Taiwan University via Coursera Machine Learning Capstone: An Intelligent Application with Deep Learning
University of Washington via Coursera Прикладные задачи анализа данных
Moscow Institute of Physics and Technology via Coursera Leading Ambitious Teaching and Learning
Microsoft via edX