eduzhai > Applied Sciences > Engineering >

AM-DCGAN Analog Memristive Hardware Accelerator for Deep Convolutional Generative Adversarial Networks

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 3 pages

Abstract: Generative Adversarial Network (GAN) is a well known computationally complexalgorithm requiring signficiant computational resources in softwareimplementations including large amount of data to be trained. This makes itsimplementation in edge devices with conventional microprocessor hardware a slowand difficult task. In this paper, we propose to accelerate the computationallyintensive GAN using memristive neural networks in analog domain. We present afully analog hardware design of Deep Convolutional GAN (DCGAN) based onCMOS-memristive convolutional and deconvolutional networks simulated using180nm CMOS technology.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×