framework
active
framework:recurrent-processing-theory-rptRecurrent Processing Theory (RPT)
A neuroscientific theory claiming that recurrent processing in perceptual areas is necessary and sufficient for conscious vision.
Neighborhood — ranked by edge-count
Papers (2)
paper
- Taking AI Welfare Seriouslymentions
Concepts (2)
concept
- RPT-1: Input modules using algorithmic recurrenceassociated_withIndicator derived from RPT: use of algorithmic recurrence in input modules.
- Indicator: perceptual organization beyond feature extraction.
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.
- A computational HOT claiming that consciousness depends on metacognitive monitoring distinguishing reliable perceptual representations from noise.
- Theory that perception and cognition involve predictive coding; listed with indicators in Butlin et al. 2023.
- Foundational framework consisting of systems (wires), processes (boxes), and composition (wirings); basis for quantum and compositional reasoning.
- Prior work on recurrently generated position encodings; cited as precedent for TEM-t's recurrent position encoding method.
- Claim formalizing the Anima Labs idea that transformers are effectively recurrent due to K/V stream.
- Machine learning paradigm where agents learn to maximize cumulative reward through interaction.
- Transformers are recurrent through autoregression because the K/V stream provides horizontal information flow across positions, even though each forward pass is feedforward.
- Process theories can be derived from variational principles in a straightforward manner with biological plausibility.hypothesis0.712Paper's core methodological hypothesis: gap between normative and process-level theories can be bridged.