Mostafa-Samir/DNC-tensorflow

A TensorFlow implementation of DeepMind's Differential Neural Computers (DNC)

51
/ 100
Established

This project offers a specialized neural network architecture for AI researchers and machine learning practitioners exploring advanced memory capabilities in models. It takes in structured data sequences and processes them using a neural network with dynamic external memory, outputting insights into how these memory mechanisms function and generalize. It's designed for those investigating neural network design beyond standard architectures.

580 stars. No commits in the last 6 months.

Use this if you are an AI researcher or machine learning engineer looking to implement and experiment with a Differentiable Neural Computer (DNC) for tasks requiring dynamic memory and generalization.

Not ideal if you are a practitioner seeking an off-the-shelf solution for common machine learning problems without delving into advanced neural network architecture research.

AI Research Neural Network Architecture Deep Learning Machine Learning Engineering Cognitive AI
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

580

Forks

161

Language

Jupyter Notebook

License

MIT

Last pushed

Jan 08, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Mostafa-Samir/DNC-tensorflow"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.