Psychiatry Research, Analytics & eXperimental Innovation Society
From theory into tools that reach patients.
PRAXIS is an undergraduate research group working at the intersection of machine learning, neuroscience, and clinical mental health. We build, test, and publish — and we train the researchers who will keep doing it.
Four things we intend to be true within three years. Everything the group does is measured against them.
- 01
Peer-reviewed research published with undergraduate members leading the work.
- 02
At least one clinical tool built, deployed, and validated on real patient data.
- 03
A recognized undergraduate hub for computational psychiatry, with a pipeline that outlasts any single cohort.
- 04
Members who go on to top PhD programs, NIH intramural positions, and industry research roles.
Original research
Applying machine learning to clinical populations. Current work covers vocal biomarker extraction and dopaminergic modeling of anhedonia. Members join an existing project or pitch their own.
Journal club
A twenty-paper sequence taking undergraduates from reinforcement learning and active inference through to reading and writing primary literature.
Speaker series
Biweekly technical talks with principal investigators and postdocs from the NIMH and leading research institutions. Recorded, with consent, as a podcast.
@comp-psych
Open-source computational psychiatry resources and reference implementations.
Repositorycomp-psych-syllabus
The twenty-paper undergraduate curriculum: foundations of RL, active inference, and computational models of mood.
RepositoryClinical-Whisper-Pipeline
The code behind ClinicalWhisper — the speech model adapted for clinical interview audio.
- Who
Undergraduates interested in computational psychiatry — machine learning, neuroscience, or clinical mental health.
- What
The journal club first, then a seat on a live project — or a pitch of your own at the monthly session.
- How
Email czhou732@usc.edu with a sentence about what you want to work on.