Spiking neural networks provide accurate and time-efficient models for whisker stimulus classification of the awake mouse

  • Machine learning algorithms have great potential for classifying brain activity, and lightweight classifier algorithms, requiring little computational resources, can be used on low-energy neuromorphic hardware designed for implantable neuroprosthetics. One of these efficient algorithms, the Liquid State Machine, implements the concept of Spiking Neural Networks and has been shown to achieve outstanding results on the task of whisker stimulus detection from the mouse barrel cortex, a widely used model system. While this is promising for neuroprosthetics, it has been unclear how a Spiking Neural Network or other machine learning algorithms perform on data recorded from awake mice and how trained models generalize across individuals, the latter being relevant to transferring trained models to new hardware. Using laminar multi-electrode local field potential recordings obtained from four mice performing a single-whisker detection task, we benchmarked the performance of a collection of lightweight classification algorithms. We found that the Liquid State Machine, a generalized linear model, and the time series classifier ROCKET are the most accurate for stimulus detection. Among those, the Liquid State Machine achieved the fastest model training and inference runtime and provided robust accuracy across individual mice. Additional analyses show that there is no significant improvement in using multiple cortical layers as input for the model and that 40 ms of stimulus recording is sufficient to maintain high detection accuracy.

Download full text files

Export metadata

Additional Services

Search Google Scholar
Metadaten
Author:Steffen Albrecht, Jens R. Vandevelde, Edoardo Vecchi, Gabriele Berra, Davide Bassetti, Maik C. Stüttgen, Heiko J. Luhmann, Illia Horenko
URN:urn:nbn:de:hbz:386-kluedo-135751
ISSN:1662-453X
Parent Title (English):Frontiers in Neuroscience
Publisher:Frontiers
Document Type:Article
Language of publication:English
Date of Publication (online):2026/04/01
Year of first Publication:2026
Publishing Institution:Rheinland-Pfälzische Technische Universität Kaiserslautern-Landau
Date of the Publication (Server):2026/09/08
Issue:20
Article Number:1605209
Page Number:13
Source:10.3389/fnins.2026.1605209
Faculties / Organisational entities:Kaiserslautern - Fachbereich Mathematik
DDC-Cassification:6 Technik, Medizin, angewandte Wissenschaften / 620 Ingenieurwissenschaften und Maschinenbau
Collections:Open-Access-Publikationsfonds
Licence (German):Lizenz nach Originalpublikation