Artificial Kuramoto Oscillatory Neurons

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Miyato, Takeru, Löwe, Sindy, Geiger, Andreas, Welling, Max
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908368011001856
author Miyato, Takeru
Löwe, Sindy
Geiger, Andreas
Welling, Max
author_facet Miyato, Takeru
Löwe, Sindy
Geiger, Andreas
Welling, Max
contents It has long been known in both neuroscience and AI that ``binding'' between neurons leads to a form of competitive learning where representations are compressed in order to represent more abstract concepts in deeper layers of the network. More recently, it was also hypothesized that dynamic (spatiotemporal) representations play an important role in both neuroscience and AI. Building on these ideas, we introduce Artificial Kuramoto Oscillatory Neurons (AKOrN) as a dynamical alternative to threshold units, which can be combined with arbitrary connectivity designs such as fully connected, convolutional, or attentive mechanisms. Our generalized Kuramoto updates bind neurons together through their synchronization dynamics. We show that this idea provides performance improvements across a wide spectrum of tasks such as unsupervised object discovery, adversarial robustness, calibrated uncertainty quantification, and reasoning. We believe that these empirical results show the importance of rethinking our assumptions at the most basic neuronal level of neural representation, and in particular show the importance of dynamical representations. Code:https://github.com/autonomousvision/akorn Project page:https://takerum.github.io/akorn_project_page/
format Preprint
id arxiv_https___arxiv_org_abs_2410_13821
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Artificial Kuramoto Oscillatory Neurons
Miyato, Takeru
Löwe, Sindy
Geiger, Andreas
Welling, Max
Machine Learning
Artificial Intelligence
It has long been known in both neuroscience and AI that ``binding'' between neurons leads to a form of competitive learning where representations are compressed in order to represent more abstract concepts in deeper layers of the network. More recently, it was also hypothesized that dynamic (spatiotemporal) representations play an important role in both neuroscience and AI. Building on these ideas, we introduce Artificial Kuramoto Oscillatory Neurons (AKOrN) as a dynamical alternative to threshold units, which can be combined with arbitrary connectivity designs such as fully connected, convolutional, or attentive mechanisms. Our generalized Kuramoto updates bind neurons together through their synchronization dynamics. We show that this idea provides performance improvements across a wide spectrum of tasks such as unsupervised object discovery, adversarial robustness, calibrated uncertainty quantification, and reasoning. We believe that these empirical results show the importance of rethinking our assumptions at the most basic neuronal level of neural representation, and in particular show the importance of dynamical representations. Code:https://github.com/autonomousvision/akorn Project page:https://takerum.github.io/akorn_project_page/
title Artificial Kuramoto Oscillatory Neurons
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2410.13821