framework
active
framework:self-priorSelf-Prior
The key novel contribution: an internal model that learns the density of familiar multisensory experiences and drives mark-removal behavior through mismatch with the free energy principle
Neighborhood — ranked by edge-count
Papers (1)
paper
Methods (2)
method
- Cross-Modal SamplingsupportsTechnique used to demonstrate that the self-prior captures visual–proprioceptive associations by recovering visual appearance from proprioception alone
- The self-prior is implemented as a GPT-like transformer that autoregressively models the joint distribution of the unified latent state
Concepts (8)
concept
- Self-Other DistinctionimplementsThe implicit capacity the self-prior implements by assigning high density to familiar self-states and low density to non-self states
- Probabilistic Body SchemaimplementsThe paper frames the self-prior as a probabilistic body schema capturing visual–proprioceptive associations
- Density Model of Self-ExperienceimplementsThe self-prior functions as a density model over the agent's familiar multisensory states in latent space
- Predecessor paper introducing the self-prior concept for goal-directed behavior emergence
- Predictive Coding Account of Self-Recognitionanalogous_toApps and Tsakiris's proposal that self-recognition can be modeled probabilistically under the free energy principle
- Kinesthetic-Visual MatchingimplementsA core requirement of the inductive theory of mirror self-recognition, implemented by the self-prior's visual-proprioceptive associations
- Multisensory IntegrationimplementsThe self-prior learns associations between visual and proprioceptive modalities without explicit design
- Preferred DistributionextendsIn active inference, the distribution over goal states; here replaced by the learned self-prior rather than a hand-specified prior
Claims (1)
claim
- Theoretical justification for implementing the self-prior in latent rather than observation space
Frameworks (1)
framework
- Active InferenceextendsFoundational framework by Karl Friston; the paper extends it to three hierarchical levels for modeling meta-awareness.
Artifacts (1)
artifact
- Released simplified robot-based implementation to support reproducibility
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Beliefs about states before data; used to transcribe task instructions into agent's generative model
- Cognitive bifurcation event where second-order contextual constraints reorganize semantic space, establishing weighted alternatives for action.
- Target distribution over states or outcomes encoded in the generative model; goal states.
- Process of reifying one's identity as an independent self; meditation practices aim to decrease selfing.
- Central interpretive claim of the paper, supported by EFE decrease after sticker removal
- The interior awareness, consciousness, and felt identity that each person experiences; absent from mechanistic cosmology.
- Structural prior over QRF deployments constraining all measurements to respect a self/environment partition; formalisation of the belief in a separate self
- Theoretical interpretation linking the self-prior to the established body schema concept