Examples gallery#

The EEGDash gallery is the runnable, narrative half of the docs: the Concepts chapter explains why a decision matters, the API reference enumerates every public symbol, and the gallery you’re reading shows the choices in motion against real BIDS-curated EEG records. Every script under examples/ is a sphinx-gallery tutorial – meaning it executes top to bottom on every documentation build, and the captured first figure is the thumbnail you see below.

The intended path: read the curated Tutorials in order, dip into How-to recipes when you have a specific question, then scale up using the Applied research projects, the EEG2025 and EEG2026 Foundation Challenges pipelines, and the High-performance computing track.

How to read this gallery

Reading order. Tutorials are sorted by category and numbered (plot_00_*, plot_10_*, …). Inside a category they’re sequenced beginner-first; the file numbers are the intended path.
Cards show the captured first figure. Sphinx-gallery stores the first matplotlib figure as the thumbnail, so the card preview is the literal output of running the script. A branded fallback is shown when the tutorial produces no figure.
Difficulty. Each section header states the difficulty range (1 = absolute beginner, 3 = advanced / foundation-model tier).

Tutorials (curated learning path)#

Seven categories, ordered the way we would teach them: install, load, decode events, decode state, engineer features, evaluate rigorously, then scale to transfer and foundation models.

Choose your path#

Your goal	Start with	Then read
Load my first dataset	Start Here	Core Decoding Workflow
Train a classifier safely	Core Decoding Workflow	Evaluation on recorded EEG
Extract classical features	Feature Engineering	How-To Guides
Run on a cluster	How-To Guides	HPC tutorials
Join EEG2025	Transfer, Foundation Models, and EEG2025	EEG2025 Foundation Challenge
Prepare for EEG/EMG 2026	EEG/EMG Foundation Challenge 2026	Official NeuralBench guides

🚀 Learn the basics

Start with the absolute beginner tutorials.

Start Here

🔬 Run an applied project

Dive into real-world research case studies.

Applied Projects

⚡ Scale on HPC

Move from local scripts to cluster-wide jobs.

HPC tutorials

🏆 Prepare for EEG/EMG 2026

Run the four announced track companions.

EEG/EMG Foundation Challenge 2026

Start Here#

Difficulty 1. Three short lessons that take you from a fresh install to a working PyTorch DataLoader over real EEG records: find datasets and records, load one recording and inspect it, then turn an EEGDashDataset into windows and a dataloader. CPU-only, each runs in under a few minutes.

Find a small cohort with the EEGDash API

Inspect your first EEG recording

From EEGDash to a PyTorch DataLoader

Core Decoding Workflow#

Difficulty 1-2. The canonical EEG decoding pipeline in four lessons: preprocess and window, split without subject leakage, train a baseline against chance, and persist prepared data for reuse. The leakage-safe split lesson is the rubric anchor for E3.27 invariants and Cisotto and Chicco 2024’s evaluation guidance.

Preprocess and window recorded EEG

Split real windows without subject leakage

Train a baseline on real SSVEP trials

Save and reload prepared EEG windows

Resting-State and State Decoding#

Difficulty 1. The canonical beginner decoding lesson: eyes-open versus eyes-closed classification on resting-state EEG, decoded from alpha-rhythm differences with a band-power baseline.

Decode eyes open and eyes closed from recorded resting EEG

Feature Engineering#

Difficulty 1-2. EEGDash’s feature extraction package as a first-class option, not an afterthought to deep learning. Three lessons cover feature tables from windows, preprocessor and dependency trees that avoid recomputation, and a scikit-learn / LightGBM baseline straight from the feature table.

Extract features from real EEG trials

Share spectral preprocessing with a feature tree

Fit scikit-learn to the saved real feature table

Evaluation and Benchmarking#

Difficulty 2-3. Five lessons that treat decoding evaluation as a core skill, drawing on MOABB (Chevallier, Aristimunha et al. 2024). Builds from a single split toward benchmark-grade pipeline comparison: within-subject, cross-subject, cross-session, learning curves, and a paired Wilcoxon comparison of two pipelines.

Within-subject decoding on real trials

Cross-subject decoding on real SSVEP recordings

Transfer a decoder between recorded sessions

Learning curves from real training subjects

Compare pipelines on paired real subject folds

Pass EEGDash recordings into a MOABB paradigm

Transfer, Foundation Models, and EEG2025#

Difficulty 3. Six advanced lessons on transfer learning and foundation-model fine-tuning, framed around the EEG2025 Foundation Challenge: EEGChallengeDataset basics, cross-task transfer (Challenge 1), participant-level p-factor regression, fine-tuning a Braindecode pretrained model, and adapting the published REVE checkpoint. Builds on Schirrmeister et al. 2017.

Which recordings belong to an EEG2025 mini release?

Does resting-state pretraining transfer to reaction time?

How do I evaluate participant-level p-factor regression?

How do I fine-tune a published pretrained EEG encoder?

How do I adapt a pretrained EEG encoder with a linear probe?

How do I export recorded EEG for NeuroAI interoperability?

How do I fine-tune a published EEG foundation model (REVE)?

How-to recipes#

Task-focused snippets that assume you already know the basics: how to download a dataset, run preprocessing on SLURM, parallelize feature extraction, use the HPC cache, and work offline. Each guide answers a single question; cross-link with the HPC track when relevant.

Download a real EEG subset and inspect its cache

Measure parallel feature extraction on recorded EEG

Stage a real EEG recording onto job-local storage

Open a staged recording in an independent offline process

Applied research projects#

Project-style examples that target a concrete scientific question – age regression, p-factor prediction, sex classification, P300 transfer, clinical-catalog summary – with realistic data sizes, runtimes, and limitations. Treat them as starting points, not prescriptive recipes.

Predict observed age (years) from real EEG features

Summarize a real clinical EEG catalogue

Exploratory eye-state decoding in an outcome-selected participant

Familiar vs unfamiliar faces with EEGPrep and ShallowFBCSPNet

P300 transfer between participants with MMD adaptation

Regress observed p-factor with a neural EEG decoder

Predict observed p-factor from real EEG features

Classify recorded sex metadata from real EEG

EEG2025 Foundation Challenge#

End-to-end pipelines for the two EEG2025 Foundation Challenge tracks: cross-task transfer learning (passive to active), and participant-held-out externalizing prediction. Both tutorials fit small baselines on real challenge recordings.

EEG2025 Challenge 1: predict observed reaction time

EEG2025 Challenge 2: a real participant-level baseline

EEG/EMG Foundation Challenge 2026#

Runnable EEGDash companions for the four announced 2026 tracks: EEG-to-image retrieval, cross-session BCI decoding, sleep-onset regression, and EMG-to-pose regression. Each tutorial uses recorded public data and points to NeuralBench for official execution and scoring.

Track 1: retrieve actual viewed images from recorded EEG

Track 2: a public motor-imagery warm-up for session transfer

Track 3: predict time remaining until the first N2 epoch

Track 4: predict real hand-joint trajectories from wrist EMG

High-performance computing#

Reference setup for running EEGDash on shared HPC clusters: SLURM submission scripts (CPU and GPU), a Dockerfile, and a tutorial showing how to combine the on-disk cache with batch scheduling for an eyes-open / eyes-closed run.

Eyes-open versus eyes-closed decoding on a cluster