SOURCE-LINKED INTELLIGENCE

Unsupervised Continual Learning with Growing Self-Organizing Maps and Synthetic Replay

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

This work presents a generative continual learning framework based on growing self-organizing maps (GSOMs) that are augmented with learned distributional statistics as well as encoder-decoder models for class-incremental learning. The proposed approach enables exemplar-free replay using distributional statistical memory, which eliminates the need to store raw data. Each GSOM unit maintains its own mean, variance, and covariance estimates, which are subsequently used to generate synthetic samples for replay; in encoder-decoder configurations, these samples are then decoded back into the input s

Read original source ↗ Open in workspace

recordType

paper

region

Global