REVISTA
AI

   
Redirigiendo al acceso original de articulo en 17 segundos...
Inicio  /  AI  /  Vol: 4 Par: 2 (2023)  /  Artículo
ARTÍCULO
TITULO

FatNet: High-Resolution Kernels for Classification Using Fully Convolutional Optical Neural Networks

Riad Ibadulla    
Thomas M. Chen and Constantino Carlos Reyes-Aldasoro    

Resumen

This paper describes the transformation of a traditional in silico classification network into an optical fully convolutional neural network with high-resolution feature maps and kernels. When using the free-space 4f system to accelerate the inference speed of neural networks, higher resolutions of feature maps and kernels can be used without the loss in frame rate. We present FatNet for the classification of images, which is more compatible with free-space acceleration than standard convolutional classifiers. It neglects the standard combination of convolutional feature extraction and classifier dense layers by performing both in one fully convolutional network. This approach takes full advantage of the parallelism in the 4f free-space system and performs fewer conversions between electronics and optics by reducing the number of channels and increasing the resolution, making this network faster in optics than off-the-shelf networks. To demonstrate the capabilities of FatNet, it was trained with the CIFAR100 dataset on GPU and the simulator of the 4f system. A comparison of the results against ResNet-18 shows 8.2 times fewer convolution operations at the cost of only 6% lower accuracy. This demonstrates that the optical implementation of FatNet results in significantly faster inference than the optical implementation of the original ResNet-18. These are promising results for the approach of training deep learning with high-resolution kernels in the direction toward the upcoming optics era.

 Artículos similares

       
 
Lin Xu, Shanxiu Ma, Zhiyuan Shen and Ying Nan    
The role of air traffic controllers is to direct and manage highly dynamic flights. Their work requires both efficiency and accuracy. Previous studies have shown that fatigue in air traffic controllers can impair their work ability and even threaten flig... ver más
Revista: Aerospace

 
Eike Blomeier, Sebastian Schmidt and Bernd Resch    
In the early stages of a disaster caused by a natural hazard (e.g., flood), the amount of available and useful information is low. To fill this informational gap, emergency responders are increasingly using data from geo-social media to gain insights fro... ver más
Revista: Information

 
Woonghee Lee and Younghoon Kim    
This study introduces a deep-learning-based framework for detecting adversarial attacks in CT image segmentation within medical imaging. The proposed methodology includes analyzing features from various layers, particularly focusing on the first layer, a... ver más
Revista: Applied Sciences

 
Mengping Huang, Shuai Ma, Jinrong He, Wei Xue, Xueyan Hou, Yuqi Zhang, Xiaofeng Liu, Heping Bai and Ran Li    
Amino acids found in minor coarse cereals are essential for human growth and development and play a crucial role in efficient and rapid quantitative detection. Surface-enhanced Raman spectroscopy (SERS) enables nondestructive, efficient, and rapid sample... ver más
Revista: Applied Sciences

 
Lei Yang, Mengxue Xu and Yunan He    
Convolutional Neural Networks (CNNs) have become essential in deep learning applications, especially in computer vision, yet their complex internal mechanisms pose significant challenges to interpretability, crucial for ethical applications. Addressing t... ver más
Revista: Applied Sciences