Unsupervised Cognition

Alfredo Ibias, Roger Aylagas, Guillem Ramirez-Miranda, Enric Guinovart, Eduard Alarcon

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Unsupervised learning, representation learning, cognition models

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: A novel method for unsupervised learning, based on novel theories of the brain

Abstract: Unsupervised learning methods have a soft inspiration in cognition models. To this day, the most successful unsupervised learning methods revolve around clustering samples in a mathematical space. In this paper we propose a primitive-based unsupervised learning approach inspired by novel cognition models. This representation-centric approach models the input space constructively as a distributed hierarchical structure in an input-agnostic way. We compared our approach with the current state-of-the-art in unsupervised learning: K-Means for tabular data and IIC for image data. We show how our proposal performs better in average than any of the alternatives. We also evaluate some cognition-like properties of our proposal that other algorithms lack, even supervised learning ones.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 3689