Nanophotonic Media for Artificial Neural Inference · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/1810.07815/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTNanophotonic Media for Artificial Neural Inference — mentioned by rahimialihttps://news.ycombinator.com/item?id=20429365urn:hackerpapers:mention:1810.07815:20429365Sat, 13 Jul 2019 18:15:36 GMT<p>They implement a trained dense multilayer neural net wit ReLU activations in silicon photonics. They evaluate it on MNIST. They use graphene to approximate the ReLUs. The device is a few microns on each side. The 2D image is first converted to a 1D wavefront by some external means, then launched into the side of the device. Training happens in digital computer, by simulating the behavior of the device. Full paper: https://arxiv.org/pdf/1810.07815.pdf</p><p><a href="https://hackerpaper.kaipfister.de/p/1810.07815/">Paper and discussion history</a>. A mention is not an endorsement.</p>physics.optics