Continual learning baselines and strategies from popular papers, using Avalanche. We include EWC, SI, GEM, AGEM, LwF, iCarl, GDumb, and other strategies.

Official Pytorch implementations of MRN: Multiplexed Routing Network for Incremental Multilingual Text Recognition (ICCV 2023)

DEPRECATED & OBSOLETE! Previously StackStorm Enterprise (EWC) Workflow Editor. Now integrated directly into StackStorm OSS Core platform (st2web).

Keras-based framework for implementing continual learning methods.

Implementation of ews weight constraint mentioned in recent Deep Mind paper: http://www.pnas.org/content/early/2017/03/13/1611835114.full.pdf

comparative evaluation of incremental machine learning methods

Tensorflow 1.x implementation of EWC, evaluated on permuted MNIST

This respository hosts the Trust List for the EWC Large Scale Pilots and is co-founded by EU Commission

A spaCy library for Named Entity Recognition with Elastic Weight Consolidation.

European Waste Codes

A short script to search for optimal values of lambda in the sequential learning technique Elastic Weight Consolidation

A comparative evaluation of continual learning strategies to mitigate catastrophic forgetting in neural networks.

Login y registro creado mediante Node y EJS, el diseño es simple debido a que el enfoque va mas al sistema de logeo y sus permisos

Continual learning for PyTorch models. Wrap once. Train forever.

Continual Reinforcement Learning for Adaptive Ocean Thermal Energy Conversion Control using PPO and Elastic Weight Consolidation

ZERO — a chess engine that taught itself chess from nothing. No human games. No opening theory. No endgame tables. Pure self-play reinforcement learning on a single consumer GPU.

A continual learning thesis project evaluating pre-trained ViT-Tiny with adapters and EWC for reducing catastrophic forgetting in sequential image classification.

Self-improving ML pipeline — captures production signals, auto-curates training data via active learning, and runs incremental LoRA fine-tuning with EWC regression guards.

Modular, reproducible continual learning experiment pipeline in Python to study catastrophic forgetting and compare strategies like EWC and GEM. Designed for rapid experiment composition, clean ablations, and local, config-driven runs with tracked outputs.