method
active
method:bowtie-architecture-compression-during-learning-creative-reinterpretation-during-recall-and-generalizationBowtie architecture: compression during learning; creative reinterpretation during recall and generalization
Neighborhood — ranked by edge-count
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 compression-based architectural pattern in which complex, high-dimensional information passes through a low-dimensional bottleneck hub, requiring creative reinterpretation or reconstruction during decompression. The framework appears across biological signaling, neural development, evolution, and machine learning (particularly autoencoders), formalizing how systems achieve memory generalization and information efficiency through constrained information flow.
- Examples of bowtie hubs at subcellular scales (e.g., Vmem, ATP, calcium).
- Example from Table 1.
- Showed transformer representations predict brain representations in language areas; motivates Discussion about cortex as transformer.
- Bowtie analogy extended to science communication.
- Claim that the emergence of new forms, often considered mysterious, is explainable through repeated intensification of latent structure.