Deep learning in the context of nano-photonics is mostly discussed in terms of its potential for inverse design of photonic devices or nano-structures. Many of the recent works on machine-learning inverse design are h...Deep learning in the context of nano-photonics is mostly discussed in terms of its potential for inverse design of photonic devices or nano-structures. Many of the recent works on machine-learning inverse design are highly specific, and the drawbacks of the respective approaches are often not immediately clear. In this review we want therefore to provide a critical review on the capabilities of deep learning for inverse design and the progress which has been made so far. We classify the different deep-learning-based inverse design approaches at a higher level as well as by the context of their respective applications and critically discuss their strengths and weaknesses. While a significant part of the community’s attention lies on nano-photonic inverse design, deep learning has evolved as a tool for a large variety of applications. The second part of the review will focus therefore on machine learning research in nano-photonics "beyond inverse design." This spans from physics-informed neural networks for tremendous acceleration of photonics simulations, over sparse data reconstruction, imaging and "knowledge discovery" to experimental applications.展开更多
We demonstrate the fabrication of a new DNA sensor that is based on the optical interactions occurring between oligonucleotide-coated NaYF4:Yb^(3+);Er^(3+) upconversion nanoparticles and the two-dimensional dichalcoge...We demonstrate the fabrication of a new DNA sensor that is based on the optical interactions occurring between oligonucleotide-coated NaYF4:Yb^(3+);Er^(3+) upconversion nanoparticles and the two-dimensional dichalcogenide materials,MoS_(2) and WS_(2).Monodisperse upconversion nanoparticles were functionalized with single-stranded DNA endowing the nanoparticles with the ability to interact with the surface of the two-dimensional materials via van der Waals interactions leading to subsequent quenching of the upconversion fluorescence.By contrast,in the presence of a complementary oligonucleotide target and the formation of double-stranded DNA,the upconversion nanoparticles could not interact with MoS_(2) and WS_(2),thus retaining their inherent fluorescence properties.Utilizing this sensor we were able to detect target oligonucleotides with high sensitivity and specificity whilst reaching a concentration detection limit as low as 5 mol·L^(-1),within minutes.展开更多
基金CALMIP Toulouse(p20010)Engineering and Physical Sciences Research Council(EP/M009122/1)Deutsche Forschungsgemeinschaft(WI 5261/1-1)。
文摘Deep learning in the context of nano-photonics is mostly discussed in terms of its potential for inverse design of photonic devices or nano-structures. Many of the recent works on machine-learning inverse design are highly specific, and the drawbacks of the respective approaches are often not immediately clear. In this review we want therefore to provide a critical review on the capabilities of deep learning for inverse design and the progress which has been made so far. We classify the different deep-learning-based inverse design approaches at a higher level as well as by the context of their respective applications and critically discuss their strengths and weaknesses. While a significant part of the community’s attention lies on nano-photonic inverse design, deep learning has evolved as a tool for a large variety of applications. The second part of the review will focus therefore on machine learning research in nano-photonics "beyond inverse design." This spans from physics-informed neural networks for tremendous acceleration of photonics simulations, over sparse data reconstruction, imaging and "knowledge discovery" to experimental applications.
基金Antonios G.Kanaras,Otto L.Muskens and Davide Giust would like to acknowledge funding from BBSRC(Grant No.BB/N021150/1).
文摘We demonstrate the fabrication of a new DNA sensor that is based on the optical interactions occurring between oligonucleotide-coated NaYF4:Yb^(3+);Er^(3+) upconversion nanoparticles and the two-dimensional dichalcogenide materials,MoS_(2) and WS_(2).Monodisperse upconversion nanoparticles were functionalized with single-stranded DNA endowing the nanoparticles with the ability to interact with the surface of the two-dimensional materials via van der Waals interactions leading to subsequent quenching of the upconversion fluorescence.By contrast,in the presence of a complementary oligonucleotide target and the formation of double-stranded DNA,the upconversion nanoparticles could not interact with MoS_(2) and WS_(2),thus retaining their inherent fluorescence properties.Utilizing this sensor we were able to detect target oligonucleotides with high sensitivity and specificity whilst reaching a concentration detection limit as low as 5 mol·L^(-1),within minutes.
