About This Document
- sl:arxiv_author : Geoffrey Hinton
- sl:arxiv_firstAuthor : Geoffrey Hinton
- sl:arxiv_num : 2102.12627
- sl:arxiv_published : 2021-02-25T01:51:22Z
- sl:arxiv_summary : This paper does not describe a working system. Instead, it presents 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. 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@en
- sl:arxiv_title : How to represent part-whole hierarchies in a neural network@en
- sl:arxiv_updated : 2021-02-25T01:51:22Z
- sl:bookmarkOf : https://arxiv.org/abs/2102.12627
- sl:creationDate : 2022-08-16
- sl:creationTime : 2022-08-16T17:02:47Z
Documents with similar tags (experimental)