quote
active
quote:ultimately-we-would-like-to-understand-neural-networks-well-enough-to-be-able-to-intentionally-design-themUltimately, we would like to understand neural networks well enough to be able to intentionally design them.
Vision statement in the conclusion.
Source paper
extracted_fromRelated 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.
- The paper's central thesis statement, presented prominently after the abstract
- Central motivating question for the circuits research program
- Extends convergence argument to brain-machine alignment
- Question about the cognitive capabilities of distributed networks.
- Strategic claim about the relative importance of motif-level abstraction over circuit-level analysis
Cross-corpus bridges (3)
same_concept_as · Nomic cosineExternal markdown files that talk about the same concept as this entity.
- aboutblank_kbCan artificial neural networks produce flexible designs and problem-solving machines rather than solutions to specific problems?questions/can-artificial-neural-networks-produce-flexible-designs-and.md0.841
- aboutblank_kbCan we develop artificial neural networks whose output determines machines that solve problems rather than specific solutions?questions/can-we-develop-artificial-neural-networks-whose-output.md0.829
- aboutblank_kbHow can we develop artificial neural networks whose output is not specific solutions but seeds determining flexible problem-solving machines?questions/how-can-we-develop-artificial-neural-networks-whose.md0.814