How to represent part-whole hierarchies in a neural network by Geoffrey Hinton

Recommendable! Food for thought! Well written! Interesting combination of different approaches! This paper is solely written by Geoffrey Hinton!

Perhaps a culmination of his work of over 30 years on part-whole hierarchies! This paper covers a lot of subjects (incl. the 13th of David Hilbert's problems).

"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. ..."

[2102.12627] How to represent part-whole hierarchies in a neural network