Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy

arxiv:2312.10549

Original source · Paper JSON

Data, training, optimization · 2023-12-16

Cites (0) · Cited by (0)

Complete cleaned Markdown · Source Markdown including bibliography

Read in parts

1. Part 1
2. Part 2
3. Part 3
4. Part 4
5. Part 5
6. Part 6
7. Part 7
8. Part 8
9. Part 9

Contents

• Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy
• Abstract
• 1 Introduction
• 2 Related work
• 3 Taxonomic Organization
• 3.1 Rehearsal
• 3.1.1 Pseudo-rehearsal
• 3.1.2 Mini-rehearsal
• 3.2 Distance-based
• 3.3 Sub-networks
• 3.3.1 Soft Sub-networks
• 3.3.2 Hard Sub-networks
• 3.4 Dynamic Networks
• 3.5 Hybrid Approaches
• 3.5.1 Enhancing Distance-based using Rehearsal
• 3.5.2 Enhancing Distance-based using Dynamic Networks
• 3.5.3 Enhancing Dynamic Networks using Rehearsal
• 3.5.4 Enhancing Sub-networks using Rehearsal
• 3.5.5 Growth Sub-networks using Dynamic Networks
• 3.5.6 Combining Sub-networks, Dynamic Networks, and Rehearsal
• 4 Final Considerations