chameleonTK / continual-learning-for-HAR

A continual model for human activity recognition (called HAR-GAN). It is based on a technique called `generative replay` which two models (classifier and generator) are trainined in the same time to keep learning a new task but also retrain previously learned knwoledge.
18Updated 2 years ago

Alternatives and similar repositories for continual-learning-for-HAR:

Users that are interested in continual-learning-for-HAR are comparing it to the libraries listed below