# Self-Generating Brain-Imaging Dataset **Entity class:** Machine-learning architecture **Domain:** Neuroimaging / Self-supervision **Maturity:** Developed ## Definition A self-generating brain-imaging dataset is produced when a model uses one learned direction, such as image-to-fMRI encoding, to manufacture additional training pairs for the reverse decoding task. ## Mechanism and significance The feedback can reduce dependence on scarce scanner time while requiring safeguards against self-reinforcing model error. ## Relationships - **Research dossier:** [[research/ASI and RSI Timeline Research Moonshots|ASI and RSI Timeline Research Moonshots]] - **Ontology route:** [[ASI and RSI Timeline Ontology#Neural Decoding and Cognitive Systems|Neural Decoding and Cognitive Systems]] - **Primary fields:** [[Neural Decoding]] · [[Brain-Computer Interfaces]] · [[Functional Magnetic Resonance Imaging]] - **Adjacent concepts:** [[Reverse Brain Encoder]] · [[Synthetic fMRI Training Data]] · [[Visual-Cortex Reconstruction]] · [[Perception Decoding]] ## Sources and provenance - [[research/ASI and RSI Timeline Research Moonshots|ASI and RSI Timeline Research Moonshots]] — immediate source for this node's role in the broadcast research map. ## Evidence boundary The research dossier establishes why this entity or concept belongs in the Moonshots ontology. Time-sensitive organizational, product, policy, and performance claims should be checked against the linked primary source or a current authoritative source before reuse as settled fact.