Enhanced machine learning library tailored for data streams, featuring a Python API integrated with MOA backend support. This unique combination empowers users to leverage a wide array of existing algorithms efficiently while fostering the development of new methodologies in both Python and Java.
MOA is an open source framework for Big Data stream mining. It includes a collection of machine learning algorithms (classification, regression, clustering, outlier detection, concept drift detection and recommender systems) and tools for evaluation.
Hydra is a framework for elegantly configuring complex applications
JPype is cross language bridge to allow Python programs full access to Java class libraries.
Lee, A., Gomes, D. H. M., & Zhang, D. Y. (2022). Balancing the Stability-Plasticity Dilemma with Online Stability Tuning for Continual Learning. Proceedings of 2022 International Joint Conference on Neural Networks (IJCNN)
Lee, A., Gomes, H. M., Zhang, Y., & Kleijn, W. B. (2025). Kolmogorov-Arnold Networks Still Catastrophically Forget but Differently from MLP. Proceedings of the AAAI Conference on Artificial Intelligence, 39(17), 18053-18061. https://doi.org/10.1609/aaai.v39i17.33986
SurpriseNet is a class incremental continual learning technique. It allows a neural network to learn from a stream or sequence of classes rather than a traditional static dataset. The main challenge it solves is differentiating classes that were never presented side-by-side.
A library for Bayesian neural network layers and uncertainty estimation in Deep Learning extending the core of PyTorch
Avalanche: an End-to-End Library for Continual Learning.
eXtremely Minimal Hugo theme: about 140 lines of code in total, including HTML and CSS (with no dependencies)
:ledger: Sphinx source parser for Jupyter notebooks
A scheduler for GPU/CPU tasks
Simple (and cheap!) neural network uncertainty estimation
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).
Continual learning baselines and strategies from popular papers, using Avalanche. We include EWC, SI, GEM, AGEM, LwF, iCarl, GDumb, and other strategies.
A machine learning package for streaming data in Python. The other ancestor of River.
A minimal yet resourceful implementation of diffusion models (along with pretrained models + synthetic images for nine datasets)
An Extendible (General) Continual Learning Framework based on Pytorch - official codebase of Dark Experience for General Continual Learning
My GitHub for handing in assignments for meta-heuristic algorithms
A brain-inspired version of generative replay for continual learning with deep neural networks (e.g., class-incremental learning on CIFAR-100; PyTorch code).
Split-and-Bridge strategy for comparison
Gothello is a combination of the games of "Go" and "Othello"