Few-shot neuromorphic vision in a nonlinear photonic network laser
Wai Kit Ng, Jakub Dranczewski, Anna Fischer, T. V. Raziman, Dhruv Saxena, Tobias Farchy, Kilian Stenning, Jonathan Peters, Heinz Schmid, Will R. Branford, Mauricio Barahona, Kirsten Moselund, Riccardo Sapienza, Jack C. Gartside · 2026
Read Few-shot neuromorphic vision in a nonlinear photonic network laser by Wai Kit Ng, Jakub Dranczewski, Anna Fischer, T. V. Raziman, Dhruv Saxena, Tobias Farchy, Kilian Stenning, Jonathan Peters, Heinz Schmid, Will R. Branford, Mauricio Barahona, Kirsten Moselund, Riccardo Sapienza, Jack C. Gartside (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13544200.txt.
Description
Wai Kit Ng and co-authors build a laser network that sees the way a retina does, learning from a handful of examples. Their 2026 paper draws on retinal design: ganglion cells sharpen features by suppressing their neighbors, and the cells' varied responses make biological vision strong when data is scarce. Artificial intelligence hardware rarely copies that trick.
In their system, competing lasing modes in a random photonic network act as the neurons, mutually inhibiting as they fight for the light. The chip-scale scheme, compatible with silicon, performs feature detection, few-shot classification, and segmentation. Light itself does the computing, at the speed and thrift photonics promises.
Catalog record
| CREATOR | Wai Kit Ng, Jakub Dranczewski, Anna Fischer, T. V. Raziman, Dhruv Saxena, Tobias Farchy, Kilian Stenning, Jonathan Peters, Heinz Schmid, Will R. Branford, Mauricio Barahona, Kirsten Moselund, Riccardo Sapienza, Jack C. Gartside |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 67 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |