paper-with-me

Papers

DAD vision: opto-electronic co-designed computer vision with division adjoint method

2022-11-04 · Zihan Zang, Haoqiang Wang, Yunpeng Xu

The miniaturization and mobility of computer vision systems are limited by the heavy computational burden and the size of optical lenses. Here, we propose to use a ultra-thin diffractive optical element to implement passive optical convolution. A division adjoint opto-electronic co-design method is also proposed. In our simulation experiments, the first few convolutional layers of the neural network can be replaced by optical convolution in a classification task on the CIFAR-10 dataset with no power consumption, while similar performance can be obtained.

📄 PDF Abstract BibTeX arXiv:2211.03576

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Analog readout for optical reservoir computers

2012-12-01 · NeurIPS 2012 12 · Anteo Smerieri, François Duport, Yvon Paquot, Benjamin Schrauwen 외

Reservoir computing is a new, powerful and flexible machine learning technique that is easily implemented in hardware. Recently, by using a time-multiplexed architecture, hardware reservoir computers have reached perform…

Direct Kernel Optimization: Efficient Design for Opto-Electronic Convolutional Neural Networks

2025-11-03 · Ali Almuallem, Harshana Weligampola, Abhiram Gnanasambandam, Wei Xu 외 arxiv

Hybrid opto-electronic neural networks combine optical front-ends with electronic back-ends to perform vision tasks, but joint end-to-end (E2E) optimization of optical and electronic components is computationally expensi…

Monocular Depth Estimation

Izhikevich-Inspired Optoelectronic Neurons with Excitatory and Inhibitory Inputs for Energy-Efficient Photonic Spiking Neural Networks

2021-05-03 · Yun-jhu Lee, Mehmet Berkay On, Xian Xiao, Roberto Proietti 외

We designed, prototyped, and experimentally demonstrated, for the first time to our knowledge, an optoelectronic spiking neuron inspired by the Izhikevich model incorporating both excitatory and inhibitory optical spikin…

Symmetry-Constrained Generation of Diverse Low-Bandgap Molecules with Monte Carlo Tree Search

2024-10-11 · Akshay Subramanian, James Damewood, Juno Nam, Kevin P. Greenman 외

Organic optoelectronic materials are a promising avenue for next-generation electronic devices due to their solution processability, mechanical flexibility, and tunable electronic properties. In particular, near-infrared…

Identifying and understanding the positive impact of defects and traps for perovskites optoelectronic devices

2020-12-10 · YH Deng

Abstract: Defects are generally regarded to have negative impact on carrier recombination, charge-transport and ion migration in perovskite materials, which thus lower the efficiency and stability of perovskite optoelect…