Acceso al sitio web del Consejo de Políticas de Infraestructura

   
Redirigiendo al acceso original de articulo en 24 segundos...
Inicio  /  Applied Sciences  /  Vol: 11 Par: 8 (2021)  /  Artículo
ARTÍCULO
TITULO

Training and Inference of Optical Neural Networks with Noise and Low-Bits Control

Danni Zhang    
Yejin Zhang    
Ye Zhang    
Yanmei Su    
Junkai Yi    
Pengfei Wang    
Ruiting Wang    
Guangzhen Luo    
Xuliang Zhou and Jiaoqing Pan    

Resumen

Optical neural networks (ONNs) are getting more and more attention due to their advantages such as high-speed and low power consumption. However, in a non-ideal environment, the noise and low-bits control may heavily lead to a decrease in the accuracy of ONNs. Since there is AD/DA conversion in a simulated neural network, it needs to be quantified in the model. In this paper, we propose a quantitative method to adapt ONN to a non-ideal environment with fixed-point transmission, based on the new chip structure we designed previously. An MNIST hand-written data set was used to test and simulate the model we established. The experimental results showed that the quantization-noise model we established has a good performance, for which the accuracy was up to about 96%. Compared with the electrical method, the proposed quantization method can effectively solve the non-ideal ONN problem.

PÁGINAS
pp. 0 - 0
REVISTAS SIMILARES
Algorithms
Information
Aerospace

 Artículos similares

       
 
Jinseo Choi, Donghyeok An and Donghyun Kang    
With the advancement of deep learning (DL), researchers and engineers in the marine industry are exploring the application of DL technologies to their specific applications. In general, the accuracy of inference using DL technologies is significantly dep... ver más

 
Philipp Gabler, Bernhard C. Geiger, Barbara Schuppler and Roman Kern    
Superficially, read and spontaneous speech?the two main kinds of training data for automatic speech recognition?appear as complementary, but are equal: pairs of texts and acoustic signals. Yet, spontaneous speech is typically harder for recognition. This... ver más
Revista: Information

 
Ali Abbasi Tadi, Saroj Dayal, Dima Alhadidi and Noman Mohammed    
The vulnerability of machine learning models to membership inference attacks, which aim to determine whether a specific record belongs to the training dataset, is explored in this paper. Federated learning allows multiple parties to independently train a... ver más
Revista: Information

 
Yiming Liu, Hongtao Shan, Feng Nie, Gaoyu Zhang and George Xianzhi Yuan    
The current popular approach to the extraction of document-level relations is mainly based on either a graph structure or serialization model method for the inference, but the graph structure method makes the model complicated, while the serialization mo... ver más
Revista: Information

 
Zhuo Li, Hengyi Li and Lin Meng    
Currently, with the rapid development of deep learning, deep neural networks (DNNs) have been widely applied in various computer vision tasks. However, in the pursuit of performance, advanced DNN models have become more complex, which has led to a large ... ver más
Revista: Computers