A5000920105- Neural dynamics and brain function
- Neural Networks and Applications
- EEG and Brain-Computer Interfaces
- Neural Networks and Reservoir Computing
- Transcranial Magnetic Stimulation Studies
- Muscle activation and electromyography studies
- Action Observation and Synchronization
- Machine Learning in Healthcare
- Artificial Intelligence in Healthcare and Education
- Neuroscience and Neural Engineering
- Functional Brain Connectivity Studies
- Neurological disorders and treatments
- Fault Detection and Control Systems
- Blind Source Separation Techniques
- AI in cancer detection
- Explainable Artificial Intelligence (XAI)
- Fungal and yeast genetics research
- Time Series Analysis and Forecasting
- Piezoelectric Actuators and Control
- Gene Regulatory Network Analysis
- Data Stream Mining Techniques
- Domain Adaptation and Few-Shot Learning
- Infrared Target Detection Methodologies
- Bioinformatics and Genomic Networks
- Robot Manipulation and Learning
University of Tübingen
2018-2025
TH Bingen University of Applied Sciences
2024
Hertie Institute for Clinical Brain Research
2021-2024
Hochschule Bonn-Rhein-Sieg
2020
Saarland University
2018
<title>Abstract</title> <bold>Background:</bold>Transcranial magnetic stimulation (TMS) is an established method for noninvasive brain stimulation, used investigating and treating disorders. Recently, multi-locus TMS (mTMS) has expanded the capabilities of by employing array overlapping coils, enabling delivery pulses at different cortical locations without physical coil movement. We aimed to design, construct, deploy mTMS device a five-coil clinical environment, emphasizing safety system....
Abstract Background With the burgeoning interest in personalized treatments for brain network disorders, closed-loop transcranial magnetic stimulation (TMS) represents a promising frontier. Relying on real-time adjustment of parameters based signal decoding, success this approach depends identification precise biomarkers timing optimally. Objective We aimed to develop and validate supervised machine learning framework individualized prediction motor excitability states, leveraging broad...
Research on transcranial magnetic stimulation (TMS) combined with encephalography feedback (EEG-TMS) has shown that the phase of sensorimotor mu rhythm is predictive corticospinal excitability. Thus, if subject-specific optimal known, can be timed to more efficient. In this paper, we present a closed-loop algorithm determine linked highest excitability few trials. We used Bayesian optimization as an automated, online search tool in EEG-TMS simulation experiment. From sample 38 participants,...
Brain state-dependent transcranial magnetic stimulation (TMS) holds promise for enhancing neuromodulatory effects by synchronizing with specific features of cortical oscillations derived from real-time electroencephalography (EEG). However, conventional approaches rely on open-loop systems static parameters, assuming that pre-determined EEG universally indicate high or low excitability states. This one-size-fits-all approach overlooks individual neurophysiological differences and the dynamic...
A critical challenge for any intelligent system is to infer structure from continuous data streams. Theories of event-predictive cognition suggest that the brain segments sensorimotor information into compact event encodings, which are used anticipate and interpret environmental dynamics. Here, we introduce a SUrprise-GAted Recurrent neural network (SUGAR) using novel form counterfactual regularization. We test model on hierarchical sequence prediction task, where sequences generated by...
Much is known about the regulatory elements controlling cell cycle in fission yeast (Schizosaccharomyces pombe). This regulation mainly done by (cyclin-dependent kinase/cyclin) complex (Cdc2/Cdc13) that activates specific target genes and proteins via phosphorylation events during a time-dependent manner. However, more work still needed to complement existing gaps current gene network be able overcome abnormalities its growth, repair development, i.e. explain many phenomena including mitotic...
We introduce REPRISE, a REtrospective and PRospective Inference SchEme, which learns temporal event-predictive models of dynamical systems. REPRISE infers the unobservable contextual event state accompanying predictive that best explain recently encountered sensorimotor experiences retrospectively. Meanwhile, it optimizes upcoming motor activities prospectively in goal-directed manner. Here, is implemented by recurrent neural network (RNN), forward contingencies generated different simulated...
Our brain receives a dynamically changing stream of sensorimotor data. Yet, we perceive rather organized world, which segment into and as events. Computational theories cognitive science on event-predictive cognition suggest that our forms generative, models by segmenting data suitable chunks contextual experiences. Here, introduce hierarchical, surprise-gated recurrent neural network architecture, this process develops compact compressions distinct event-like contexts. The architecture...