Brain pattern recognition for neuroscience research
Cortex reads resting-state brain connectivity and identifies patterns associated with autism — a 227M-parameter transformer trained on 1,545 real fMRI subjects. Three research tools. No clinical claims.
Forward, and inverse
AQAL predicts how a neurodiverse brain experiences a stimulus. Cortex runs the other direction — it reads an existing scan and characterizes the neural pattern.
Two complementary halves of the same pipeline: one maps stimulus to brain, the other maps brain to classification.
Video, audio, or text in. Predicts neurodiverse response. For spaces, therapy, sensory audits.
Connectivity in. Identifies ASD-associated patterns. For stratification, QC, biomarkers.
Three apps, one model
Each tool targets a specific research workflow, all powered by the same Cortex v1 backbone.
Cohort Stratifier
Embed each subject in a 256-dim latent space, then cluster across the cohort to find neural subgroups. Autism is a spectrum — Cortex quantifies where each subject sits on it.
Atypicality Flagger
Reconstruction-error scoring flags subjects whose connectivity is atypical. Use for quality control on large datasets, outlier detection, and preprocessing validation.
Biomarker Explorer
Integrated-gradient analysis reveals which ROI-pair connections drive classification, consolidating scattered autism connectivity literature into testable hypotheses.
Cortex Architecture
A 227M-parameter transformer over Fisher-z connectivity (100-ROI Schaefer atlas), pooled into a subject embedding and branched into three joint heads.
Classifier
ASD probability head (BCE loss) — the direct autism-association signal.
Subject encoder
256-dim embedding used for cohort stratification and subtype clustering.
Reconstructor
Rebuilds the 4,950-dim connectivity — its error is the QC / atypicality signal.
Honest disclosure
What Cortex is, and what it is not. Read this before trusting a number.
Not for clinical diagnosis
~63% validation accuracy on held-out ABIDE subjects is useful for research, not diagnosis. ADOS-2 / ADI-R remain the clinical standard.
Cohort is ABIDE I + II
Predominantly male (~91%), mostly North American / European sites, ages 5–64. Generalization to underrepresented populations is not validated.
Sites harmonized, not erased
Residual site bias may remain after harmonization. Use caution when applying to new acquisition protocols.
ASD vs TD is a simplification
Real neurodiversity is spectral. The 256-dim embedding reflects that far better than the binary classifier logit.
Start with your data
Upload connectivity features. Explore subtypes, flag outliers, discover biomarkers. No signup.