Random memory adaptation model inspired by the paper: "Memory-based parameter adaptation (MbPA)"
-
Updated
Mar 13, 2018 - Python
Random memory adaptation model inspired by the paper: "Memory-based parameter adaptation (MbPA)"
An implementation of the paper "Overcoming catastrophic forgetting in neural networks" (DeepMind, 2016), using Pytorch framework.
SupportNet: solving catastrophic forgetting in class incremental learning with support data
Supervised learning in PyTorch with prioritized memory replay.
A PyTorch implementation of the ECCV 2018 publication "Memory Aware Synapses: Learning what (not) to forget"
Keras-based framework for implementing continual learning methods.
Continual Learning methods using Episodic Memory (CLEM) in PyTorch
Repo for competition track Lifelong Robotic Vision, IROS 2019.
Simulation code for Limbacher, T. and Legenstein, R. (2020). Emergence of Stable Synaptic Clusters on Dendrites Through Synaptic Rewiring
This is repository contains code for experiment to evaluate catastrophic forgetting in neural networks.
Code for the paper "Incremental Learning Techniques for Semantic Segmentation", Michieli U. and Zanuttigh P., ICCVW, 2019
towards models that can gracefully forget
Implementation for the paper "SpaceNet: Make Free Space For Continual Learning" in PyTorch.
A simple experiment to compare Artificial and Spiking Neural Networks in Sequential and Few-Shot Learning.
[IWANN 2021] Reducing catastrophic forgetting in 3D point cloud objects with help of semantic information
detecting domain boundaries during inference
theoretical framework for continual learning / incremental learning
Continual Learning with Echo State Networks experiments
Code for ECML/PKDD 2020 Paper --- Continual Learning with Knowledge Transfer for Sentiment Classification
Add a description, image, and links to the catastrophic-forgetting topic page so that developers can more easily learn about it.
To associate your repository with the catastrophic-forgetting topic, visit your repo's landing page and select "manage topics."