Continual Contrastive Anomaly Detection under Natural Data Distribution Shifts

[Neural Networks 2023] The official repository of Neural Networks Journal "Subspace Distillation for Continual Learning"

detecting domain boundaries during inference

[IWANN 2021] Reducing catastrophic forgetting in 3D point cloud objects with help of semantic information

Code for "Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsal" (ACL 2024)

Implementation for the paper "SpaceNet: Make Free Space For Continual Learning" in PyTorch.

[ICLR-2024] Official implementation of "KFC: Knowledge Reconstruction and Feedback Consolidation Enable Efficient and Effective Continual Generative Learning"

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

[ECMLPKDD 2022] "Avoiding Forgetting and Allowing Forward Transfer in Continual Learning via Sparse Networks" by by Ghada Sokar, Decebal Constantin Mocanu, and Mykola Pechenizkiy.

Repo for competition track Lifelong Robotic Vision, IROS 2019.

Supervised learning in PyTorch with prioritized memory replay.

This is the repo for the master thesis at ITA - RWTH Aachen

The ability to learn tasks in a sequential fashion is crucial to the development of artificial intelligence. Until now neural networks have not been capable of this and it has been widely thought that catastrophic forgetting is an inevitable feature of connectionist models.

This is the PyTorch implementation of our paper "Jie Du, Wei Li, Peng Liu, et al. Model projection based Federated Learning for Non-IID data" .

2024 Neurips paper on Continual Learning and Class Incremental Learning

Keras-based framework for implementing continual learning methods.

[J. Imaging 2023] The official repository for paper CL3: Generalization of Contrastive Loss for Lifelong Learning J. Imaging 2023, 9(12), 259; https://doi.org/10.3390/jimaging9120259

The official implementation of MeDQN algorithm.

An implementation of the Hopfield network in Python. Includes a lot of additional classes, functions, and structures to test Sequential Learning, Energy, and other properties of the Hopfield Network.

A simple experiment to compare Artificial and Spiking Neural Networks in Sequential and Few-Shot Learning.