Paper Review - GLOM: How to Represent Part-Whole Hierarchies in a Neural Network by Geoffrey Hinton

Through the lens of Numenta’s Thousand Brains Theory, Marcus Lewis reviews the paper “How to represent part-whole hierarchies in a neural network” by Geoffrey Hinton. By focusing on parts of the GLOM model presented in the paper, he bridges Numenta’s theory to GLOM and highlights the similarities and differences between each model’s voting mechanisms , structure and the use of neural representations. Finally, Marcus explores the idea of GLOM handling movement. Paper: Other resources mentioned: Numenta “Thousand Brains“ voting alternate version (2017): “Receptive field structure varies with layer in the primary visual cortex“ by Martinez et al.: “A Multiplexed, Heterogeneous, and Adaptive Code for Navigation in Medial Entorhinal Cortex“ by Hardcastle et al: https://ww