EEGDash: MEEG Data Archive for Neuroscience and Machine Learning

A large-scale data-sharing resource for magnetoencephalography and electroencephalography (MEEG) data hosted at the Swartz Center for Computational Neuroscience, UC San Diego. It provides curated, BIDS-formatted datasets for neuroscience research, machine learning, and deep learning applications. The archive spans three S3 buckets for platform data, an upstream archive, and competition-specific collections.

Use Cases

• Developing deep learning models for brain signal classification based on MEEG data.
• Benchmarking machine learning algorithms using preprocessed competition datasets.
• Conducting neuroscience research with curated, BIDS-formatted neuroimaging data.
• Training models for source localization or event-related potential analysis based on EEG/MEG signals.

Strengths

• Data is curated and formatted according to the BIDS standard, which facilitates interoperability.
• Archive is described as a large-scale data-sharing resource hosted at an authoritative neuroscience center.
• Includes datasets specifically adapted for machine learning benchmarks and competitions.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count, file formats, and last update date are unknown, which may limit suitability assessment.

Provenance

Source

Swartz Center for Computational Neuroscience (SCCN), UC San Diego.

Collection Method

Data contributed through the NEMAR platform and curated for the EEGDash archive.

Time Range

null

Freshness

Last update date is unknown; freshness unverified.

Geography

null