On May 7, our colleagues at Google will host a workshop on YouTube on Conceptual Understanding of Deep Learning.
How does the brain/mind (perhaps even an artificial one) work at an algorithmic level? While deep learning has produced tremendous technological strides in recent decades, there is an unsettling feeling of a lack of conceptual understanding of why it works and to what extent it will work in its current form. The goal of this workshop is to bring together theorists and practitioners to develop an understanding of the right algorithmic view of deep learning: characterizing the class of functions that can be learned; coming up with the right learning architecture that may (provably) learn multiple functions and concepts and remember them over time as humans do; and developing a theoretical understanding of language, logic, reinforcement learning, meta-learning and lifelong learning.
The speakers and panelists include Turing Award winners Geoffrey Hinton and Leslie Valiant, Gödel Prize winner Christos Papadimitriou, and experts from diverse backgrounds including machine learning and artificial intelligence, algorithms, theory, and neuroscience.
There will also be a panel discussion on the fundamental question, Is there a mathematical model for the mind? The panel will explore basic questions such as: Is there a provable algorithm that captures the essential capabilities of the mind? How do we remember complex phenomena? How is a knowledge graph created automatically? How do we learn new concepts, function and action hierarchies over time? And why do human decisions seem so interpretable?