Search engine for discovering works of Art, research articles, and books related to Art and Culture
Javascript must be enabled to continue!
Tilted-Mode All-Optical Diffractive Deep Neural Networks
View through CrossRef
Diffractive deep neural networks (D2NNs) typically adopt a densely cascaded arrangement of diffractive masks, leading to multiple reflections of diffracted light between adjacent masks, thereby affecting the network’s inference capability. It is challenging to fully simulate this multiple-reflection phenomenon. To eliminate this phenomenon, we designed tilted-mode all-optical diffractive deep neural networks (T-D2NNs) and proposed a theoretical model for diffraction propagation in the tilted mode. Simulation results indicate that T-D2NNs address the performance degradation caused by interlayer reflections in D2NNs constructed with high-index diffractive masks. In classification tasks, T-D2NNs achieve better classification results compared to D2NNs that consider interlayer reflections.
Title: Tilted-Mode All-Optical Diffractive Deep Neural Networks
Description:
Diffractive deep neural networks (D2NNs) typically adopt a densely cascaded arrangement of diffractive masks, leading to multiple reflections of diffracted light between adjacent masks, thereby affecting the network’s inference capability.
It is challenging to fully simulate this multiple-reflection phenomenon.
To eliminate this phenomenon, we designed tilted-mode all-optical diffractive deep neural networks (T-D2NNs) and proposed a theoretical model for diffraction propagation in the tilted mode.
Simulation results indicate that T-D2NNs address the performance degradation caused by interlayer reflections in D2NNs constructed with high-index diffractive masks.
In classification tasks, T-D2NNs achieve better classification results compared to D2NNs that consider interlayer reflections.
Related Results
Diffractive Optics: From Basic Research to Practical Applications
Diffractive Optics: From Basic Research to Practical Applications
A diffractive optical element is an optical device that utilizes interference and diffraction, rather than refraction or reflection, to shape an emerging wavefront. In this talk we...
Hybrid Optical Diffractive Neural Networks (HODNNs) for Speckle Reconstruction and Physical Auto-encoding
Hybrid Optical Diffractive Neural Networks (HODNNs) for Speckle Reconstruction and Physical Auto-encoding
Abstract
All-optical Diffractive Deep Neural Network (D2NN) architecture can learn to implement various functions after the deep learning-based design of passive diffractiv...
Fuzzy Chaotic Neural Networks
Fuzzy Chaotic Neural Networks
An understanding of the human brain’s local function has improved in recent years. But the cognition of human brain’s working process as a whole is still obscure. Both fuzzy logic ...
Design, Analysis, and Manufacturing of Diffractive Achromatic Optical Systems
Design, Analysis, and Manufacturing of Diffractive Achromatic Optical Systems
The increasing resolution requirements of imaging optical systems must be satisfied by expanding the aperture of the optical system according to Rayleigh’s criterion, and larger ap...
On the role of network dynamics for information processing in artificial and biological neural networks
On the role of network dynamics for information processing in artificial and biological neural networks
Understanding how interactions in complex systems give rise to various collective behaviours has been of interest for researchers across a wide range of fields. However, despite ma...
Diffractive Optics in Free-Space OptoElectronic Computing Systems
Diffractive Optics in Free-Space OptoElectronic Computing Systems
Optical interconnections have been shown to have advantages over electrical interconnections in terms of speed, energy, and density for global links1. In addition, the flexibility ...
ACM SIGCOMM computer communication review
ACM SIGCOMM computer communication review
At some point in the future, how far out we do not exactly know, wireless access to the Internet will outstrip all other forms of access bringing the freedom of mobility to the way...
Proton–proton, pion–proton and pion–pion diffractive collisions at ultrahigh energies
Proton–proton, pion–proton and pion–pion diffractive collisions at ultrahigh energies
The LHC energies are those at which the asymptotic regime in hadron–hadron diffractive collisions (pp, πp, ππ) might be switched on. Based on results of the Dakhno–Nikonov eikonal ...