PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR, BI-R, ER, A-GEM, iCaRL, Generative Classifier) in three different scenarios.

A flexible, adaptive classification system for dynamic text classification

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

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

Continual Hyperparameter Selection Framework. Compares 11 state-of-the-art Lifelong Learning methods and 4 baselines. Official Codebase of "A continual learning survey: Defying forgetting in classification tasks." in IEEE TPAMI.

Elastic weight consolidation technique for incremental learning.

PyTorch implementation of a VAE-based generative classifier, as well as other class-incremental learning methods that do not store data (DGR, BI-R, EWC, SI, CWR, CWR+, AR1, the "labels trick", SLDA).

#WORK IN PROGRESS PyTorch Implementation of Supervised and Deep Q-Learning EWC(Elastic Weight Consolidation), introduced in "Overcoming Catastrophic Forgetting in Neural Networks"

comparative evaluation of incremental machine learning methods

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

implementation of some classical CL methods using deepseed

Multi domain adaption of quick sentiment analysis on mutliple catagories of task like classification of the nature of the reviews regrading various objects found in Amazon website

An investigation into weight importance measures in neural networks, relating to sequential learning and interpretability.

An investigation into sequential learning of tasks using feed-forward networks built with Tensorflow

CEL Continual Learning

Reinforcement Learning with Variational Bayesian Inference and Elastic Weight Consolidation

This is the temporary version of the MINT Lab continual-learning website.

A flexible, adaptive classification system for dynamic text classification

This project investigates various continual learning methods to mitigate catastrophic forgetting

Implements regularization-based continual learning strategies that mitigate catastrophic forgetting by penalizing large parameter changes. Includes reproducible implementations of EWC, Synaptic Intelligence (SI), and Memory Aware Synapses (MAS) with experiment scripts and benchmark evaluations on Split-MNIST, Permuted-MNIST, and CIFAR-100.