Bio-inspired, task-free continual learning through activity regularization

DOI10.1007/S00422-023-00973-WMaRDI QIDQ6549428zbMATH OpenFDO

Authors Francesco Lässig, Pau Vilimelis Aceituno, Martino Sorbaro, Benjamin F. Grewe

Publication date 3 June 2024

Published in Biological Cybernetics (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1007/S00422-023-00973-W

zbMATH Keywords

activity regularizationbio-inspiredcontinual learningfeedbacklateral inhibitionsparsity

Mathematics Subject Classification ID

Memory and learning in psychology (91E40) Feedback control (93B52)

Recommendations

• Hierarchically structured task-agnostic continual learning
• Progressive learning: a deep learning framework for continual learning
• Adversarial Feature Alignment: Avoid Catastrophic Forgetting in Incremental Task Lifelong Learning
• Overcoming catastrophic forgetting in neural networks

Cites work

• Overcoming catastrophic forgetting in neural networks
• Scikit-learn: machine learning in Python

Cited in

(3)

• Hierarchically structured task-agnostic continual learning
• A three-way decision approach for dynamically expandable networks
• What can computer vision learn from visual neuroscience? Introduction to the special issue

This page was built for publication: Bio-inspired, task-free continual learning through activity regularization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6549428)