Private Event
How to Represent Part-Whole Hierarchies in a Neural Net
Host
Bill Freeman and Phillip Isola
MIT CSAIL
Title: How to Represent Part-Whole Hierarchies in a Neural Net
Abstract:
I will present a single idea about representation which allows advances made by several different groups to be combined into an imaginary system called GLOM. The advances include transformers, neural fields, contrastive representation learning, distillation and capsules. GLOM answers the question: How can a neural network with a fixed architecture parse an image into a part-whole hierarchy which has a different structure for each image? The idea is simply to use islands of identical vectors to represent the nodes in the parse tree. The talk will discuss the many ramifications of this idea. If GLOM can be made to work, it should significantly improve the interpretability of the representations produced by transformer-like systems when applied to vision or language.
Bio:
Geoffrey Hinton is a VP Engineering Fellow at Google and University of Toronto professor emeritus. He was one of the researchers who introduced the backpropagation algorithm and the first to use backpropagation for learning word embeddings. His research group in Toronto made major breakthroughs in deep learning that revolutionized speech recognition and object classification. For his contributions to deep neural networks, he received the 2018 ACM Turing Award.
Abstract:
I will present a single idea about representation which allows advances made by several different groups to be combined into an imaginary system called GLOM. The advances include transformers, neural fields, contrastive representation learning, distillation and capsules. GLOM answers the question: How can a neural network with a fixed architecture parse an image into a part-whole hierarchy which has a different structure for each image? The idea is simply to use islands of identical vectors to represent the nodes in the parse tree. The talk will discuss the many ramifications of this idea. If GLOM can be made to work, it should significantly improve the interpretability of the representations produced by transformer-like systems when applied to vision or language.
Bio:
Geoffrey Hinton is a VP Engineering Fellow at Google and University of Toronto professor emeritus. He was one of the researchers who introduced the backpropagation algorithm and the first to use backpropagation for learning word embeddings. His research group in Toronto made major breakthroughs in deep learning that revolutionized speech recognition and object classification. For his contributions to deep neural networks, he received the 2018 ACM Turing Award.