IDSIA/modern-srwm

Official repository for the paper "A Modern Self-Referential Weight Matrix That Learns to Modify Itself" (ICML 2022 & NeurIPS 2021 Deep RL Workshop) and "Accelerating Neural Self-Improvement via Bootstrapping" (ICLR 2023 Workshop)

34
/ 100
Emerging

This project provides advanced techniques for machine learning researchers and practitioners who are experimenting with novel neural network architectures. It offers methods to build neural networks that can dynamically adjust their own internal connections (weights) as they learn, leading to more efficient and self-improving models. The intended user is a machine learning scientist or deep learning engineer focused on model development and optimization.

176 stars. No commits in the last 6 months.

Use this if you are a researcher or advanced practitioner designing and testing next-generation neural networks, especially in deep reinforcement learning or supervised learning scenarios where models need to adapt and improve over time.

Not ideal if you are looking for an off-the-shelf solution for a standard machine learning task or if you are not comfortable working with experimental deep learning architectures and custom code.

deep-learning-research neural-network-architecture reinforcement-learning-algorithms self-improving-systems machine-learning-engineering
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 14 / 25

How are scores calculated?

Stars

176

Forks

18

Language

Python

License

Last pushed

Jun 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/IDSIA/modern-srwm"

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