CALM: Continual Associative Learning Model via Sparse Distributed Memory
Αποθηκεύτηκε σε:
| Εκδόθηκε σε: | Technologies vol. 13, no. 12 (2025), p. 587-612 |
|---|---|
| Κύριος συγγραφέας: | |
| Άλλοι συγγραφείς: | |
| Έκδοση: |
MDPI AG
|
| Θέματα: | |
| Διαθέσιμο Online: | Citation/Abstract Full Text Full Text - PDF |
| Ετικέτες: |
Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3286356925 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 2227-7080 | ||
| 024 | 7 | |a 10.3390/technologies13120587 |2 doi | |
| 035 | |a 3286356925 | ||
| 045 | 2 | |b d20250101 |b d20251231 | |
| 084 | |a 231637 |2 nlm | ||
| 100 | 1 | |a Nechesov Andrey | |
| 245 | 1 | |a CALM: Continual Associative Learning Model via Sparse Distributed Memory | |
| 260 | |b MDPI AG |c 2025 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a Sparse Distributed Memory (SDM) provides a biologically inspired mechanism for associative and online learning. Transformer architectures, despite exceptional inference performance, remain static and vulnerable to catastrophic forgetting. This work introduces Continual Associative Learning Model (CALM), a conceptual framework that defines the theoretical base and integration logic for the cognitive model seeking to establish continual, lifelong adaptation without retraining by combining SDM system with lightweight dual-transformer modules. The architecture proposes an always-online associative memory for episodic storage (System 1), as well as a pair of asynchronous transformer consolidate experience in the background for uninterrupted reasoning and gradual model evolution (System 2). The framework remains compatible with standard transformer benchmarks, establishing a shared evaluation basis for both reasoning accuracy and continual learning stability. Preliminary experiments using the SDMPreMark benchmark evaluate algorithmic behavior across multiple synthetic sets, confirming a critical radius-threshold phenomenon in SDM recall. These results represent deterministic characterization of SDM dynamics in the component level, preceding the integration in the model level with transformer-based semantic tasks. The CALM framework provides a reproducible foundation for studying continual memory and associative learning in hybrid transformer architectures, although future work should involve experiments with non-synthetic, high-load data to confirm scalable behavior in high interference. | |
| 653 | |a Approximation | ||
| 653 | |a Neurons | ||
| 653 | |a Principles | ||
| 653 | |a Embedded systems | ||
| 653 | |a Associative memory | ||
| 653 | |a Artificial intelligence | ||
| 653 | |a Distance learning | ||
| 653 | |a Distributed memory | ||
| 653 | |a Benchmarks | ||
| 653 | |a Episodic memory | ||
| 653 | |a Reasoning | ||
| 700 | 1 | |a Ruponen Janne | |
| 773 | 0 | |t Technologies |g vol. 13, no. 12 (2025), p. 587-612 | |
| 786 | 0 | |d ProQuest |t Materials Science Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3286356925/abstract/embedded/J7RWLIQ9I3C9JK51?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text |u https://www.proquest.com/docview/3286356925/fulltext/embedded/J7RWLIQ9I3C9JK51?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3286356925/fulltextPDF/embedded/J7RWLIQ9I3C9JK51?source=fedsrch |