About
I'm a PhD researcher working at the intersection of neural signal processing and machine learning. My work focuses on extracting reliable information from non-invasive EEG — improving how we record it, clean it, and decode it into meaningful states.
A central thread of my research is the tripolar concentric ring electrode (TCRE): how its improved spatial resolution changes what we can classify from the scalp, particularly for overt and covert speech. Alongside this, I work on epilepsy EEG analysis and the deep-learning methods that make these signals tractable.
Research focus
- Signal & electrodes Tripolar concentric ring electrodes (TCRE) for higher-resolution, reference-free EEG acquisition.
- Speech decoding Overt vs. covert speech-state classification from EEG across electrode configurations.
- Clinical EEG Epilepsy EEG analysis and quantitative markers of neural change.
- Methods Preprocessing pipelines (MNE-Python), feature extraction, and deep-learning models for neural time series.
Selected publications
Full and up-to-date list on ORCID and Google Scholar.
Teaching
Neural Networks & EEG with Python — lecture series
An open video series building machine learning for neural signals from the ground up: from the mechanics of backpropagation to practical EEG pipelines. Made for researchers who want to understand the methods, not just call the library.
The series has reached 15,000+ learners, with an engaged audience of students and researchers in the field.
“Took a class in BCI at my university, so it’s really cool to see it actually done.” — Biomedical engineering student, UC Irvine
Contact
Open to postdoctoral positions and collaborations in EEG, BCI, and neural machine learning.