Andreas Maier

Prediction, Syntax and Semantic Grounding in the Brain and Large Language Models

The paper investigates how syntactic processing, predictive coding, and semantic grounding interact in real time using MEG-EEG and compares neural responses to a large language model.

SEMPAI: a Self-Enhancing Multi-Photon Artificial Intelligence for prior-informed assessment of muscle function and pathology

SEMPAI integrates hypothesis-driven priors into a deep learning framework to analyze multiphoton microscopy data of muscle fibers, outperforming existing methods in predictive tasks.

Deep learning based decoding of local field potential events

This paper uses an auto-encoder to decode single-trial local field potential events, revealing neural activity patterns and information flux direction in rodents and humans.

Intrinsic noise improves speech recognition in a computational model of the auditory pathway

This study shows that intrinsic noise improves speech recognition in a deep neural network model of the auditory pathway, suggesting potential benefits for both biological and machine learning systems.

Analysis and Visualization of Sleep Stages based on Deep Neural Networks

This study develops a deep learning method to analyze and visualize sleep stages using EEG data, showing it can estimate sleep cycle lengths and detect disturbances.

Analysis of continuous neuronal activity evoked by natural speech with computational corpus linguistics methods

The paper combines natural speech and MEG to create a corpus of speech-evoked neuronal activity using computational corpus linguistics methods.