Author Correction: Implanted microelectrode arrays in reinnervated muscles allow separation of neural drives from transferred polyfunctional nerves

2026-05-20 · Source: Machine learning : nature.com subject feeds · Field: Science & Research — Engineering & Applied Sciences, Health & Medical Research · Depth: Expert, quick

Summary

An author correction has been issued for an article titled "Implanted microelectrode arrays in reinnervated muscles allow separation of neural drives from transferred polyfunctional nerves," originally published in Nature Biomedical Engineering on 24 October 2025. The correction, published on 20 May 2026, addresses a typographical error found in the "Task-dependent latent neural manifolds" section of the Methods. Specifically, the value "10−5" was incorrectly presented as "105" in the text describing the mean squared error (m.s.e.) curve calculation. The amended text clarifies that the optimal number of latent variables corresponds to the maximum number for which the m.s.e. remained lower than 10−5.

Key takeaway

For research scientists replicating or building upon the methods described in the original Nature Biomedical Engineering article, be aware of the corrected typographical error. The mean squared error (m.s.e.) threshold for determining the optimal number of latent variables is 10−5, not 105. Ensure your calculations or interpretations align with this precise value to maintain methodological accuracy.

Key insights

A typographical error in a biomedical engineering article's methods section regarding a numerical threshold has been corrected.

Topics

• Author Correction
• Typographical Error
• Nature Biomedical Engineering
• Latent Variables
• Mean Squared Error
• Research Methods

Best for: Research Scientist

Related on AIssential

• Hybrid knowledge- and data-driven modelling for robust spike detection and sorting in human C-fiber microneurography — A hybrid pipeline improves C-fiber spike sorting in microneurography by combining physiological knowledge with machine learning for robust detection.
• Author Correction: Generalizable and scalable protein stability prediction with rewired protein generative models — A published article received a correction due to an outdated figure being uploaded.
• Neurosoft Bioelectronics raises $7.5M for scalable brain-computer interfaces — Neurosoft's soft, minimally invasive brain interfaces collect scalable, high-quality neural data to build cortical foundation models and improve clinical outcomes.
• Latent space mapping of interpretable structural coordinates from stochastic single-molecule signals — Latent-space mapping resolves stochastic signal warping in nanopore sensors, enabling interpretable molecular coordinate systems.
• From Baseline to Follow-Up: Counterfactual Spine DXA Image Synthesis in UK Biobank Using a Causal Hierarchical Variational Autoencoder — The CHVAE model synthesizes anatomically plausible, causally consistent spine DXA images by intervening on age, addressing anatomical variation challenges.
• Physics-Informed Neural Networks for Chemotherapy Pharmacokinetics: Benchmarking the Clinical Estimator and Exposing Parameter Identifiability — PINNs offer a uniform framework for pharmacokinetics, matching traditional methods on linear problems and exposing identifiability issues in nonlinear models.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Machine learning : nature.com subject feeds.