PyTorch implementation of various methods for continual learning (XdG, EWC, online EWC, SI, LwF, GR, GR+distill, RtF, ER, A-GEM, iCaRL).

✅ ✅ ✅ A massive repo filled with notes on everything from coding to philosophy to psychology to marketing to product

Evaluate three types of task shifting with popular continual learning algorithms.

VOSK Speech Recognition Toolkit

A collection of incremental learning paper implementations.

A clean and simple library for Continual Learning

CVPR 2020 Continual Learning Challenge - Submit your CL algorithm today!

Steven C. Y. Hung, Cheng-Hao Tu, Cheng-En Wu, Chien-Hung Chen, Yi-Ming Chan, and Chu-Song Chen, "Compacting, Picking and Growing for Unforgetting Continual Learning," Thirty-third Conference on Neural Information Processing Systems, NeurIPS 2019

A brain-inspired version of generative replay for continual learning with deep neural networks (class-incremental learning on CIFAR-100; PyTorch code).

1'st Place approach for CVPR 2020 Continual Learning Challenge

Implementation of "Episodic Memory in Lifelong Language Learning"(NeurIPS 2019) in Pytorch

A pytorch compatible data loader to create sequence of tasks for Continual Learning

ContinualAI official website

Towards increasing stability of neural networks for continual learning: https://arxiv.org/abs/2006.06958.pdf

A PyTorch implementation of the ECCV 2018 publication "Memory Aware Synapses: Learning what (not) to forget"

A PyTorch implementation of the CVPR 2017 publication "Expert Gate: Lifelong Learning with a Network of Experts"

Steven C. Y. Hung, Jia-Hong Lee, Timmy S. T. Wan, Chein-Hung Chen, Yi-Ming Chan and Chu-Song Chen. "Increasingly Packing Multiple Facial-Informatics Modules in A Unified Deep-Learning Model via Lifelong Learning" 2019 ACM on International Conference on Multimedia Retrieval

lifelong learning: record and analysis of my knowledge structure

AI Physicist, a paradigm with algorithms for learning theories from data, by Wu and Tegmark (2019)

Repository containing code for the paper "Meta-Learning with Sparse Experience Replay for Lifelong Language Learning".

AR1* with Latent Replay, implemented in PyTorch

Normalization Matters in Zero-Shot Learning

"The Unreasonable Effectiveness of Sparse Dynamic Synapses for Continual Learning" paper project.

Keras-based framework for implementing continual learning methods.

Neural Topic Modeling with Continual Lifelong Learning (ICML 2020)

Continual Learning utilities

M.Sc Thesis - 3D_DEN: Open-ended 3D Object Recognition using Dynamically Expandable Networks

Code for "Evolving Inborn Knowledge For Fast Adaptation in Dynamic POMDP Problems"

Official implementation of "RODEO: Replay for Online Object Detection", BMVC 2020