Bibliografie Dokumente/documents https://biblio.ub.rptu.de/index/index/ Mon, 20 Apr 2026 08:07:41 +0200 Mon, 20 Apr 2026 08:07:41 +0200 https://biblio.ub.rptu.de/frontdoor/index/index/docId/18518 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. Steffen Albrecht; Jens R. Vandevelde; Edoardo Vecchi; Gabriele Berra; Davide Bassetti; Maik C. Stüttgen; Heiko J. Luhmann; Illia Horenko article https://biblio.ub.rptu.de/frontdoor/index/index/docId/18518 Mon, 20 Apr 2026 08:07:41 +0200 https://biblio.ub.rptu.de/frontdoor/index/index/docId/18182 Wolfgang Neuser conferenceobject https://biblio.ub.rptu.de/frontdoor/index/index/docId/18182 Fri, 17 Apr 2026 09:51:53 +0200 https://biblio.ub.rptu.de/frontdoor/index/index/docId/18181 Wolfgang Neuser conferenceobject https://biblio.ub.rptu.de/frontdoor/index/index/docId/18181 Fri, 17 Apr 2026 09:39:10 +0200 https://biblio.ub.rptu.de/frontdoor/index/index/docId/18180 Wolfgang Neuser bookpart https://biblio.ub.rptu.de/frontdoor/index/index/docId/18180 Fri, 17 Apr 2026 09:27:20 +0200 https://biblio.ub.rptu.de/frontdoor/index/index/docId/18179 Wolfgang Neuser conferenceobject https://biblio.ub.rptu.de/frontdoor/index/index/docId/18179 Fri, 17 Apr 2026 09:22:03 +0200 https://biblio.ub.rptu.de/frontdoor/index/index/docId/18178 Wolfgang Neuser bookpart https://biblio.ub.rptu.de/frontdoor/index/index/docId/18178 Fri, 17 Apr 2026 09:09:52 +0200 https://biblio.ub.rptu.de/frontdoor/index/index/docId/18177 Wolfgang Neuser bookpart https://biblio.ub.rptu.de/frontdoor/index/index/docId/18177 Fri, 17 Apr 2026 08:53:52 +0200 https://biblio.ub.rptu.de/frontdoor/index/index/docId/18176 Wolfgang Neuser bookpart https://biblio.ub.rptu.de/frontdoor/index/index/docId/18176 Fri, 17 Apr 2026 08:48:04 +0200 https://biblio.ub.rptu.de/frontdoor/index/index/docId/18175 Wolfgang Neuser bookpart https://biblio.ub.rptu.de/frontdoor/index/index/docId/18175 Fri, 17 Apr 2026 08:40:50 +0200 https://biblio.ub.rptu.de/frontdoor/index/index/docId/18174 Wolfgang Neuser conferenceobject https://biblio.ub.rptu.de/frontdoor/index/index/docId/18174 Fri, 17 Apr 2026 08:22:37 +0200 https://biblio.ub.rptu.de/frontdoor/index/index/docId/18173 Wolfgang Neuser bookpart https://biblio.ub.rptu.de/frontdoor/index/index/docId/18173 Fri, 17 Apr 2026 08:13:01 +0200 https://biblio.ub.rptu.de/frontdoor/index/index/docId/18172 Wolfgang Neuser bookpart https://biblio.ub.rptu.de/frontdoor/index/index/docId/18172 Fri, 17 Apr 2026 08:05:35 +0200 https://biblio.ub.rptu.de/frontdoor/index/index/docId/18507 Olaf Grutza; Simon Graf; Stefan Paulus; Stefan Thielen; Oliver Koch article https://biblio.ub.rptu.de/frontdoor/index/index/docId/18507 Fri, 17 Apr 2026 08:03:59 +0200 https://biblio.ub.rptu.de/frontdoor/index/index/docId/18171 Wolfgang Neuser bookpart https://biblio.ub.rptu.de/frontdoor/index/index/docId/18171 Fri, 17 Apr 2026 07:57:18 +0200 https://biblio.ub.rptu.de/frontdoor/index/index/docId/18170 Wolfgang Neuser bookpart https://biblio.ub.rptu.de/frontdoor/index/index/docId/18170 Fri, 17 Apr 2026 07:39:47 +0200 https://biblio.ub.rptu.de/frontdoor/index/index/docId/18214 Simulations are an important tool in the development and design of magnetic sensors. The disadvantage of these simulations lies in frequent assumption of perfect conditions, without considering production-related variations. Depending on the system, these variations can have a significant effect on the sensor output signals, leading to an offset between simulation and reality. Running multiple simulations to cover all variations is often too time consuming. This weakness is addressed in this study. Machine learning techniques are used to train a model on production-related variations with simulated data. The model is then able to predict sensor signal deviations in real time based on the ideal signals. This allows designers to check their sensor design within the specified production variations without the need for additional time-consuming simulations. The approach is implemented using a virtual module of a supporting magnet and a GMR sen-sor array called GLM712 from Sensitec GmbH. This type of sensor is used to detect the angle of rotation and speed of tooth structures without contact. A characteristic of this type of sensor technology is the need for a specific design depending on the geometry of the tooth structure. In the manufacturing of these sensors, there are variations in sensor position, orientation and the properties of the supporting magnet, which have been shown to affect the signal. These are the variations for which the machine learning model is trained. Hagen Schmidt; Tim Becker; Jörg Seewig conferenceobject https://biblio.ub.rptu.de/frontdoor/index/index/docId/18214 Thu, 16 Apr 2026 15:27:50 +0200 https://biblio.ub.rptu.de/frontdoor/index/index/docId/18209 Tim Becker; Jannik Keber; Jörg Seewig bookpart https://biblio.ub.rptu.de/frontdoor/index/index/docId/18209 Thu, 16 Apr 2026 15:14:20 +0200 https://biblio.ub.rptu.de/frontdoor/index/index/docId/18142 Taimur K. Khan; Henning Barthel; Achim Ebert; Peter Liggesmeyer conferenceobject https://biblio.ub.rptu.de/frontdoor/index/index/docId/18142 Thu, 16 Apr 2026 14:44:40 +0200 https://biblio.ub.rptu.de/frontdoor/index/index/docId/18139 Ahmad Adee; Peter Munk; Roman Gansch; Peter Liggesmeyer conferenceobject https://biblio.ub.rptu.de/frontdoor/index/index/docId/18139 Thu, 16 Apr 2026 14:40:45 +0200 https://biblio.ub.rptu.de/frontdoor/index/index/docId/18137 Ragaad AlTarawneh; Shah Rukh Humayoun; Achim Ebert; Peter Liggesmeyer conferenceobject https://biblio.ub.rptu.de/frontdoor/index/index/docId/18137 Thu, 16 Apr 2026 14:34:26 +0200 https://biblio.ub.rptu.de/frontdoor/index/index/docId/18136 Felix Möhrle; Kai Bizik; Marc Zeller; Kai Höfig; Martin Rothfelder; Peter Liggesmeyer conferenceobject https://biblio.ub.rptu.de/frontdoor/index/index/docId/18136 Thu, 16 Apr 2026 14:32:03 +0200 https://biblio.ub.rptu.de/frontdoor/index/index/docId/18123 Michael Roth; Agus Hartoyo; Peter Liggesmeyer conferenceobject https://biblio.ub.rptu.de/frontdoor/index/index/docId/18123 Thu, 16 Apr 2026 14:21:16 +0200 https://biblio.ub.rptu.de/frontdoor/index/index/docId/18122 Michael Roth; Peter Liggesmeyer conferenceobject https://biblio.ub.rptu.de/frontdoor/index/index/docId/18122 Thu, 16 Apr 2026 14:20:18 +0200 https://biblio.ub.rptu.de/frontdoor/index/index/docId/18116 Anil Ranjitbhai Patel; Peter Liggesmeyer conferenceobject https://biblio.ub.rptu.de/frontdoor/index/index/docId/18116 Thu, 16 Apr 2026 14:17:26 +0200 https://biblio.ub.rptu.de/frontdoor/index/index/docId/18110 Jörg Caumanns; R. Walter; Matthias Rohs; Stefan Grunwald; Walter Mattauch conferenceobject https://biblio.ub.rptu.de/frontdoor/index/index/docId/18110 Thu, 16 Apr 2026 14:13:46 +0200