EurekAlert!

A federated anti-forgetting representation method based on hybrid model architecture and gradient truncation

Anti-forgetting representation learning method reduces the weight aggregation interference on model memory and augments the ...
IEEE

Unsupervised Continual Learning Using Cross-Level Discrimination and Evidential Pseudo Out-of-Distribution Detection Along With Gradient Projected Hard Attention

Abstract: Catastrophic forgetting is a prominent challenge in machine learning, where models forget previously learned knowledge when exposed to new information. Supervised Continual Learning (SCL) ...
IEEE

Gram–Schmidt Methods for Unsupervised Feature Extraction and Selection

Abstract: Feature extraction and selection in the presence of nonlinear dependencies among the data is a fundamental challenge in unsupervised learning. We propose using a Gram-Schmidt (GS) type ...