gradient-episodic-memory

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.

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.

This website applies a recommendation system and continuous learning.

GenPark AI Agent Skill - Elastic Weight Consolidation (EWC) engine calculating Fisher Information Matrix diagonal penalties to prevent catastrophic forgetting during sequential task learning.

GenPark AI Agent Skill - Continual learning experience replay buffer with streaming reservoir sampling and priority weighting to balance past vs new agent trajectories.

GenPark AI Agent Skill - Gradient Episodic Memory (GEM / A-GEM) projection engine constraining parameter updates to prevent interference with past task gradients.

GenPark AI Agent Skill - Knowledge distillation teacher-student loss engine with temperature-scaled Kullback-Leibler divergence for continual model compression and capability preservation.

GenPark AI Agent Skill - Synaptic Intelligence (SI) online path integral engine accumulating parameter trajectory contributions to protect vital synaptic pathways across tasks.

GenPark AI Agent Skill - Synaptic Intelligence (SI) online path integral engine accumulating parameter trajectory contributions to protect vital synaptic pathways across tasks.

GenPark AI Agent Skill - Gradient Episodic Memory (GEM / A-GEM) projection engine constraining parameter updates to prevent interference with past task gradients.

GenPark AI Agent Skill - Continual learning experience replay buffer with streaming reservoir sampling and priority weighting to balance past vs new agent trajectories.

GenPark AI Agent Skill - Elastic Weight Consolidation (EWC) engine calculating Fisher Information Matrix diagonal penalties to prevent catastrophic forgetting during sequential task learning.

implementation of some classical CL methods using deepseed

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

Projects