# google-deepmind/dnc

A TensorFlow implementation of the Differentiable Neural Computer.

Repository: https://github.com/google-deepmind/dnc
Canonical: https://ross.abutalabs.com/products/dnc
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2021-07-23T08:02:12+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3445, "days_push": 1867, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2531, forks 446 (observed 2026-08-28T04:06:58.933117+00:00)

## What it is
A TensorFlow implementation of the Differentiable Neural Computer (DNC), a recurrent neural network architecture with an external memory published in Nature by DeepMind. It is built from composable RNNCore modules (controller, access, temporal linkage, freeness) and includes an example training script for algorithmic tasks.

## Use cases
- implement a differentiable neural computer in tensorflow
- experiment with memory-augmented neural network architectures
- train an RNN on sequence copying tasks
- study the DNC architecture from the Nature paper
- build custom memory access modules for RNNs

## When to choose
- you want a faithful reference implementation of the DNC paper
- you work in TensorFlow/Sonnet and want pluggable RNNCore memory modules
- you're doing research on memory-augmented neural networks

## When to avoid
- you use PyTorch or JAX instead of TensorFlow
- you need actively maintained code with recent updates
- you want a production-ready sequence model rather than research code

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: deep-learning, machine-learning
- platform: python
- tags: tensorflow, sonnet, recurrent-neural-network, external-memory, research-code, deepmind, algorithms

## Member repositories
- google-deepmind/dnc (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:58.933117+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:25:19.733878+00:00, confidence not recorded.
  - readme: https://github.com/google-deepmind/dnc (fetched 2026-08-28T04:06:58.933117+00:00, sha b618e7c6d851)
- Data as of 2026-08-30T08:39:29.467469+00:00.