scholar.google.com › citations
Sep 9, 2023 · A general-purpose photonic gradient descent unit named STADIA is designed to implement the multiplication, accumulation, and subtraction operations required ...
Sep 9, 2023 · A general-purpose photonic gradient descent unit named STADIA is designed to implement the multiplication, accumulation, and subtraction operations required ...
A general-purpose photonic gradient descent unit named STADIA is designed to implement the multiplication, accumulation, and subtraction operations required ...
Simulation results show that the proposed architecture STADIA can achieve significant improvement by 9.7× in time efficiency and 147.2× in energy efficiency, ...
People also ask
Do neural networks use stochastic gradient descent?
Is gradient descent sufficient for neural network?
When should you use stochastic gradient descent?
What are the disadvantages of stochastic gradient descent?
Chengpeng Xia, Yawen Chen, Haibo Zhang, and Jigang Wu, STADIA: Photonic Stochastic Gradient Descent for Neural Network Accelerators, ACM Transactions on ...
Dec 2, 2019 · using a stochastic gradient descent method (on a conventional computer). An on-chip training with forward propagation is also proposed. (see ...
STADIA: Photonic Stochastic Gradient Descent for Neural Network Accelerators ... optical communication acceleration according to photonic effects and photonic ...
Feb 15, 2024 · This project aims to design photonic computing solutions to accelerate the training of deep learning models, which is much more computation-, memory- and ...
Jul 25, 2024 · In this paper, to provide a better understanding of optical technology used in ANN acceleration, we present a comprehensive review for the ...
STADIA: Photonic Stochastic Gradient Descent for Neural Network Acclerators, ... Efficient neural network accelerators with optical computing and communication,