Yann Harel

LSD Reconfigures Cortical Dynamics Through Faster Brain Rhythms and Increased Fractal Dimension

This study investigates how LSD alters brain dynamics using MEG and machine learning, finding increased peak frequencies, reduced oscillatory power, and changes in spectral complexity.

LSD Relaxes Structural Constraints on Brain Dynamics: A Connectome Harmonic MEG Study

This study uses MEG and connectome harmonics to show LSD reduces structure-function coupling in low-frequency brain activity, linking this to ego dissolution and altered network dynamics.

Behavioral Imitation with Artificial Neural Networks Leads to Personalized Models of Brain Dynamics During Videogame Play

This paper uses imitation learning with ANNs to model individual brain dynamics during videogame play, finding that subject-specific models better predict brain activity than generic ones.

MEEGNet: An open source python library for the application of convolutional neural networks to MEG

MEEGNet is a Python library for applying convolutional neural networks to MEG data, achieving high accuracy in classification tasks while offering interpretability tools.

Class imbalance should not throw you off balance: Choosing the right classifiers and performance metrics for brain decoding with imbalanced data

This paper evaluates the impact of class imbalance on ML performance in neuroscience, showing that Accuracy is misleading and recommending Balanced Accuracy and Random Forest with stratified cross-validation.

An open, analysis-ready, and quality controlled resource for pediatric brain white-matter research

The paper curates and provides analysis-ready diffusion MRI data for pediatric brain white-matter research, including automated quality control using a trained neural network.