Neural networks and physical systems with emergent collective computational abilities.¶
Hopfield, J. J. (1982). Neural networks and physical systems with emergent collective computational abilities. Proceedings of the National Academy of Sciences, 79(8), 2554-2558.
Cited by¶
2 citations across 2 artifacts.
Each citation links to the sentence it supports in the citing article.
Primes¶
- Associative Memory
- The defining commitment is that the key and the value inhabit the same representational space, and proximity in that space drives recall — the exact opposite of address-based lookup, where the key is an arbitrary handle bearing no relation to what it points to.
This sourceSUPPORTS markers 121, 122, 134 (energy-function attractors; representation-is-index collapse).
Supported in partVerified against the publisher's abstract
The abstract states the model yields a content-addressable memory that recovers an entire stored pattern from any subpart, which grounds the content-addressing core but not the explicit contrast with address-based lookup.
“The collective properties of this model produce a content-addressable memory which correctly yields an entire memory from any subpart of sufficient size.”
- The defining commitment is that the key and the value inhabit the same representational space, and proximity in that space drives recall — the exact opposite of address-based lookup, where the key is an arbitrary handle bearing no relation to what it points to.
- Pattern Completion (Filling the Incomplete)
- The output includes not just the next token but potentially the full sentence or response, with content (semantic coherence, grammatical structure, topic consistency) that was not explicit in the input but is implicit in the training distribution.
Supported in partVerified against the publisher's abstract
Supplies the pattern-completion principle (a stored memory recovered whole from any sufficient subpart), but not the claim's language-model specifics: tokens, grammar, topic consistency, or training distributions.
“The collective properties of this model produce a content-addressable memory which correctly yields an entire memory from any subpart of sufficient size.”
- The output includes not just the next token but potentially the full sentence or response, with content (semantic coherence, grammatical structure, topic consistency) that was not explicit in the input but is implicit in the training distribution.
Verification¶
Does it exist? Confirmed. This work's DOI resolves to a registered record, which fixes its identity. That is all it fixes.
Does it back the claim? Read against the text for 2 of 2 citations: 2 supported in part. Each verdict is shown under its citation below, with what in the work backs the sentence.
Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.
See how references were verified.
Registry ID ref:8c0e0bbea6c4 · see in the full table