Metraipolis › archive › dc_e8e495bd706d

Structured Affinity for Unsupervised Visual Class-Incremental Memory in Deep Artificial Immune Networks — arXiv:2608.20104

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.20104
License (as archived)
CC0-1.0
Archived
2026-10-18T11:48:48.586Z
SHA-256 of the archived text
a22edbc35484bd9545525a261b284c740d9029eba02c0e9ce47ec48c3142e4c8
Stable URL of this page
https://metraipolis.com/documento/dc_e8e495bd706d

How to cite

Structured Affinity for Unsupervised Visual Class-Incremental Memory in Deep Artificial Immune Networks — arXiv:2608.20104 — arXiv (en), https://arxiv.org/abs/2608.20104 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e8e495bd706d (Metraipolis archive dc_e8e495bd706d, sha256 a22edbc35484bd9545525a261b284c740d9029eba02c0e9ce47ec48c3142e4c8)
BibTeX
@misc{dce8e495bd706d,
  title = {Structured Affinity for Unsupervised Visual Class-Incremental Memory in Deep Artificial Immune Networks — arXiv:2608.20104},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.20104},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e8e495bd706d; sha256 a22edbc35484bd9545525a261b284c740d9029eba02c0e9ce47ec48c3142e4c8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20104. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Artificial immune networks (AINs) are naturally memory-forming systems, but conventional visual AINs often rely on flattened vector affinity that ignores spatial structure. This paper studies whether structured, gradient-free immune affinity can make Deep AINs viable as replay-free visual class-incremental representation-memory learners. Visual B-cells are formalized as structured templates, including shifted-template affinity, zero-normalized cross-correlation (ZNCC) filters, and feature-map binding profiles. A repertoire is treated both as memory and as a representation-inducing basis, while depth is obtained by passing binding-profile response maps to subsequent immune layers. The resulting Deep AIN exhibits adaptive latent coordinate reorganization: as new classes arrive, the binding-profile space evolves while retaining recoverable structure for earlier classes. Experiments on sklearn digits, MNIST, Fashion-MNIST, and KMNIST show that preserving response maps is critical. Scalar binding-profile variants underperform, whereas feature-map Deep AINs learn class-discriminative visual memory without replay, label-driven immune updates, or backpropagation through the immune layers. On sklearn digits, downstream probes fitted on the learned binding profiles reach 0.939 final balanced accuracy with logistic regression and 0.902 with 1-nearest-neighbour after all ten classes are encountered, with initial-class retention of 0.978. Adaptive layer-wise scale calibration further improves the two-layer feature-map Deep AIN to 0.978 balanced accuracy. With the same calibration rule, Fashion-MNIST reaches 0.814 and KMNIST reaches 0.853. These probes are external validation tools, not components of the AIN. The results identify structured affinity, response-map preservation, adaptive latent reorganization, and layer-wise scale calibration as key mechanisms for replay-free visual immune memory.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-21 in cs.LG).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.20104 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T11:47:43.388Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).