Polyra Swarms: A Shape-Based Approach to Machine Learning

2025/06/16 by Simon Klüttermann, Klüttermann, Simon, Emmanuel Müller +1
Computer Science · Engineering · #FOS: Computer and information sciences #Machine Learning (cs.LG) #Modular Robots and Swarm Intelligence #Neural Networks and Applications #Neural and Evolutionary Computing (cs.NE) #Symbolic Computation (cs.SC)

paper · pdf · doi:10.48550/arxiv.2506.13217

openalex publication_date 2025/06/16 · openalex created_date 2025/10/13 · openalex updated_date 2026/07/28

Abstract

We propose Polyra Swarms, a novel machine-learning approach that approximates shapes instead of functions. Our method enables general-purpose learning with very low bias. In particular, we show that depending on the task, Polyra Swarms can be preferable compared to neural networks, especially for tasks like anomaly detection. We further introduce an automated abstraction mechanism that simplifies the complexity of a Polyra Swarm significantly, enhancing both their generalization and transparency. Since Polyra Swarms operate on fundamentally different principles than neural networks, they open up new research directions with distinct strengths and limitations.

Citations

• On Diffusion Modeling for Anomaly Detection
• Does Deep Learning Learn to Abstract? A Systematic Probing Framework
• ADBench: Anomaly Detection Benchmark
• The Geometric Occam's Razor Implicit in Deep Learning
• Machine Learning with a Reject Option: A survey
• Diffusion Models Beat GANs on Image Synthesis
• Kepler’s Goat Herd: An exact solution to Kepler’s equation for elliptical orbits
• A Unifying Review of Deep and Shallow Anomaly Detection
• Classification-Based Anomaly Detection for General Data
• Deep Learning for Person Re-identification: A Survey and Outlook
• Deep Learning for Person Re-Identification: A Survey and Outlook
• Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey
• Deep Learning with Topological Signatures
• Variational Inference with Normalizing Flows
• The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web]
• The reflex arc concept in psychology.
• A Look at Some Data on the Old Faithful Geyser
• The perceptron: A probabilistic model for information storage and organization in the brain.
• A Comparison of Alternative Tests of Significance for the Problem of m Rankings

Related

• Optimizing collective fieldtaxis of swarming agents through reinforcement learning
• Collisionless Pattern Discovery in Robot Swarms Using Deep Reinforcement Learning
• Analysis of swarm behavior using compound eye and neural network control
• Flexible Swarm Learning May Outpace Foundation Models in Essential Tasks
• Swarm of One: Bottom-up Emergence of Stable Robot Bodies from Identical Cells