IDSIA/automated-cl
Official repository for the paper "Automating Continual Learning"
This project helps machine learning researchers overcome 'catastrophic forgetting' in AI models. If you're training models to learn new tasks sequentially, this provides methods and code to automate how models adapt without forgetting previous knowledge. It takes a machine learning model and a sequence of learning tasks, and outputs an improved model that can learn continually and efficiently. Machine learning researchers and practitioners developing adaptable AI systems for real-world scenarios would find this useful.
No commits in the last 6 months.
Use this if you are a machine learning researcher working on models that need to learn new information over time without losing previously acquired knowledge, especially in research settings.
Not ideal if you need production-ready code for immediate deployment, as this is research code with known sub-optimal implementations.
Stars
18
Forks
5
Language
Python
License
MIT
Category
Last pushed
Jun 11, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/IDSIA/automated-cl"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
galilai-group/stable-pretraining
Reliable, minimal and scalable library for pretraining foundation and world models
CognitiveAISystems/MAPF-GPT
[AAAI-2025] This repository contains MAPF-GPT, a deep learning-based model for solving MAPF...
UKPLab/gpl
Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled...
larslorch/avici
Amortized Inference for Causal Structure Learning, NeurIPS 2022
svdrecbd/mhc-mlx
MLX + Metal implementation of mHC: Manifold-Constrained Hyper-Connections by DeepSeek-AI.