Brain-Inspired AI with Hyperbolic Geometry

TL;DR

This paper advocates for increased use of hyperbolic geometry in neural networks, inspired by brain structure, to enhance accuracy, efficiency, and feature representation across AI tasks.

Contribution

It highlights the potential of hyperbolic geometry in neural networks, inspired by brain organization, and provides empirical evidence of its advantages over Euclidean models.

Findings

Hyperbolic neural networks outperform Euclidean models in NLP and vision tasks.

Hyperbolic models require fewer parameters and generalize better.

Brain's hierarchical structure aligns with hyperbolic geometry, facilitating intelligence.

Abstract

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.