# Neuronal diversity can improve machine learning for physics and beyond

Source: [Neuronal diversity can improve machine learning for physics and beyond](<https://www.sota2.com/research/paper/68fa70711e209131cea4b063>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T01:41:08.783Z

Authors: Anshul Choudhary, Anil Radhakrishnan, John F. Lindner, Sudeshna Sinha, William L. Ditto

Published: 2022-04-09T01:48:41.000Z

## Abstract

Diversity conveys advantages in nature, yet homogeneous neurons typically comprise the layers of artificial neural networks. Here we construct neural networks from neurons that learn their own activation functions, quickly diversify, and subsequently outperform their homogeneous counterparts on image classification and nonlinear regression tasks. Sub-networks instantiate the neurons, which meta-learn especially efficient sets of nonlinear responses. Examples include conventional neural networks classifying digits and forecasting a van der Pol oscillator and physics-informed Hamiltonian neural networks learning H\\'enon-Heiles stellar orbits and the swing of a video recorded pendulum clock. Such \\textit{learned diversity} provides examples of dynamical systems selecting diversity over uniformity and elucidates the role of diversity in natural and artificial systems.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2204.04348>)

[PDF](<https://arxiv.org/pdf/2204.04348.pdf>)