Brain-Inspired AI with Hyperbolic Geometry

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Joseph, Alexander, Francis, Nathan, Balay, Meijke
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917909363687424
author Joseph, Alexander
Francis, Nathan
Balay, Meijke
author_facet Joseph, Alexander
Francis, Nathan
Balay, Meijke
contents Artificial neural networks (ANNs) were inspired by the architecture and functions of the human brain and have revolutionised the field of artificial intelligence (AI). Inspired by studies on the latent geometry of the brain, in this perspective paper we posit that an increase in the research and application of hyperbolic geometry in ANNs and machine learning will lead to increased accuracy, improved feature space representations and more efficient models across a range of tasks. We examine the structure and functions of the human brain, emphasising the correspondence between its scale-free hierarchical organization and hyperbolic geometry, and reflecting on the central role hyperbolic geometry plays in facilitating human intelligence. Empirical evidence indicates that hyperbolic neural networks outperform Euclidean models for tasks including natural language processing, computer vision and complex network analysis, requiring fewer parameters and exhibiting better generalisation. Despite its nascent adoption, hyperbolic geometry holds promise for improving machine learning models through brain-inspired geometric representations.
format Preprint
id arxiv_https___arxiv_org_abs_2409_12990
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Brain-Inspired AI with Hyperbolic Geometry
Joseph, Alexander
Francis, Nathan
Balay, Meijke
Neurons and Cognition
Artificial Intelligence
I.2
Artificial neural networks (ANNs) were inspired by the architecture and functions of the human brain and have revolutionised the field of artificial intelligence (AI). Inspired by studies on the latent geometry of the brain, in this perspective paper we posit that an increase in the research and application of hyperbolic geometry in ANNs and machine learning will lead to increased accuracy, improved feature space representations and more efficient models across a range of tasks. We examine the structure and functions of the human brain, emphasising the correspondence between its scale-free hierarchical organization and hyperbolic geometry, and reflecting on the central role hyperbolic geometry plays in facilitating human intelligence. Empirical evidence indicates that hyperbolic neural networks outperform Euclidean models for tasks including natural language processing, computer vision and complex network analysis, requiring fewer parameters and exhibiting better generalisation. Despite its nascent adoption, hyperbolic geometry holds promise for improving machine learning models through brain-inspired geometric representations.
title Brain-Inspired AI with Hyperbolic Geometry
topic Neurons and Cognition
Artificial Intelligence
I.2
url https://arxiv.org/abs/2409.12990