Metraipolis › archive › dc_7f7740bb83a4
Seeing Why: Exact Evidence Maps for Quantum and Optical Image Classifiers — arXiv:2611.01993
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01993
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T11:25:13.961Z
- SHA-256 of the archived text
6c47984c9c92e570f20f28c1c03f2395e8092073d2bd6fe818a9a807d926e6df- Stable URL of this page
https://metraipolis.com/documento/dc_7f7740bb83a4
How to cite
Seeing Why: Exact Evidence Maps for Quantum and Optical Image Classifiers — arXiv:2611.01993 — arXiv (en), https://arxiv.org/abs/2611.01993 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7f7740bb83a4 (Metraipolis archive dc_7f7740bb83a4, sha256 6c47984c9c92e570f20f28c1c03f2395e8092073d2bd6fe818a9a807d926e6df)
BibTeX
@misc{dc7f7740bb83a4,
title = {Seeing Why: Exact Evidence Maps for Quantum and Optical Image Classifiers — arXiv:2611.01993},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01993},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7f7740bb83a4; sha256 6c47984c9c92e570f20f28c1c03f2395e8092073d2bd6fe818a9a807d926e6df},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01993. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
When an image classifier decides, we can usually only estimate why. For quantum and all-optical classifiers that act linearly on amplitude-encoded pictures up to the measurement, with no trained classical network before or after them, the decomposition needs no approximation: each class's probability above its no-information share splits exactly into contributions of the encoded amplitudes, shown as Born evidence maps (BEM) over the picture and measurable on the hardware that classifies. For the quadratic form behind each class probability it equals Integrated Gradients from a zero baseline, in closed form. Deleting the 5 % of pixels with the highest evidence drops accuracy from 73 % to 9 %, as occlusion does with 1,024 extra runs per picture, whereas gradient saliency removes much less. One architecture serves both: a Fourier-plane mask followed by a brickwall circuit on qubits or by phase plates on a lens bench, read by a Born headroom readout with no trained parameter; centring each picture on its own mean lets dark features count as much as bright ones. In simulation, four phase plates at a single wavelength reach 72.3 % on Caltech-10 colour photographs (96.8 % on MNIST, 86.7 % on Fashion-MNIST, 47.9 % on colour CIFAR-10). On IBM's ibm_kingston, with the mask applied before approximate loading, 300 Caltech-10 test pictures were classified at 37.7 % against 10 % by chance (56.3 % in exact simulation), and 2x2 maps of ten correctly and confidently classified pictures, estimated on the chip, agreed with the exact ones (r = 0.77). The maps also revealed a shortcut in the data. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Quantum Physics (quant-ph) ; Machine Learning (cs.LG); Optics (physics.optics). Pagina del lavoro: https://arxiv.org/abs/2611.01993 — 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 2026-11-03T11:02:37.840Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).