Deception in Objectives
Kenneth and Tim discuss how ambitious objectives in machine learning often involve deception, using the metaphor of a maze to explain the challenges in shaping reward functions and understanding neural representations. They delve into the complexities of search spaces and the subtleties that go beyond visual perception.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#038 - Professor Kenneth Stanley - Why Greatness Cannot Be Planned
Related Questions