Reference library
Testing the Genomic Bottleneck Hypothesis in Hebbian Meta-Learning
Paper summary
Tests a genomic-bottleneck hypothesis by limiting the repertoire of Hebbian learning rules and learning their synapse assignments. Joint optimization performs poorly in the studied environments, contrary to the initial expectation of improved generalization.
Relevance to the project
Direct caution for evolving reusable type mechanisms and assignment criteria together. Compare staged or constrained alternatives before claiming sharing makes evolution easier.
Related positive clustering results are separate work, not this paper's primary outcome.
Source record
- Reference ID
- pmlr-palm21a
- Archived version
- Publisher/institution PDF advertised by article metadata
- Summary provenance
- reference-library/papers/pmlr-palm21a/metadata.json · summary
- Review status
- initial orientation summary; not a critical full-paper review
- Reading scope
- Selected abstract/opening and available closing discussion/conclusion passages in the preserved text extract; broader project notes provide context. No reproduction of experiments, exhaustive methods review, or equation/figure audit.