Pith

open record

sign in
Pith Number

pith:FJL2FJIB

pith:2014:FJL2FJIBBGTXP2552KLFUPPCPV
not attested not anchored not stored refs resolved

Neural Turing Machines

Alex Graves, Greg Wayne, Ivo Danihelka

Neural networks gain an external memory bank they control through soft attention, creating end-to-end differentiable systems that learn algorithms from examples.

arxiv:1410.5401 v2 · 2014-10-20 · cs.NE

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{FJL2FJIBBGTXP2552KLFUPPCPV}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open
Portable graph bundle live · download bundle · merged state
The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

The combined system is analogous to a Turing Machine or Von Neumann architecture but is differentiable end-to-end, allowing it to be efficiently trained with gradient descent. Preliminary results demonstrate that Neural Turing Machines can infer simple algorithms such as copying, sorting, and associative recall from input and output examples.

C2weakest assumption

That the attentional read and write operations remain stable and trainable with gradient descent without the memory interactions causing vanishing gradients or optimization failure on longer sequences.

C3one line summary

Neural Turing Machines augment neural networks with differentiable external memory to learn algorithmic tasks such as copying, sorting, and associative recall from examples.

References

42 extracted · 42 resolved · 1 Pith anchors

[1] Baddeley, A., Eysenck, M., and Anderson, M. (2009). Memory . Psychology Press 2009
[2] Neural Machine Translation by Jointly Learning to Align and Translate 2014 · arXiv:1409.0473
[3] Barrouillet, P., Bernardin, S., and Camos, V. (2004). Time constraints and resource sharing in adults' working memory spans. Journal of Experimental Psychology: General , 133(1):83 2004
[4] Chomsky, N. (1956). Three models for the description of language. Information Theory, IEEE Transactions on , 2(3):113--124 1956
[5] L., and Sun, G.-Z 1992

Formal links

1 machine-checked theorem link

Cited by

75 papers in Pith

Receipt and verification
First computed 2026-07-04T19:15:22.837907Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

2a57a2a50109a777ebbdd2965a3de27d56a17e3e25ea2ad07d4ac4f0421df502

Aliases

arxiv: 1410.5401 · arxiv_version: 1410.5401v2 · doi: 10.48550/arxiv.1410.5401 · pith_short_12: FJL2FJIBBGTX · pith_short_16: FJL2FJIBBGTXP255 · pith_short_8: FJL2FJIB
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/FJL2FJIBBGTXP2552KLFUPPCPV \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 2a57a2a50109a777ebbdd2965a3de27d56a17e3e25ea2ad07d4ac4f0421df502
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "53a93bba96507fc80ece41543b44a5f42898b49b1dc9a9d6c206c597fdf88645",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.NE",
    "submitted_at": "2014-10-20T19:28:26Z",
    "title_canon_sha256": "6a74d2fab1bca245e50f298c71506d15b7c4cc97a4bb0259f2c553b41e08977b"
  },
  "schema_version": "1.0",
  "source": {
    "id": "1410.5401",
    "kind": "arxiv",
    "version": 2
  }
}