AM-DCGAN: Analog Memristive Hardware Accelerator for Deep Convolutional Generative Adversarial Networks
This addresses the problem of slow and difficult GAN implementation on edge devices for applications requiring efficient hardware acceleration.
The paper tackled the computational complexity of implementing Generative Adversarial Networks (GANs) on edge devices by proposing an analog memristive hardware accelerator, resulting in a fully analog design of a Deep Convolutional GAN simulated using 180nm CMOS technology.
Generative Adversarial Network (GAN) is a well known computationally complex algorithm requiring signficiant computational resources in software implementations including large amount of data to be trained. This makes its implementation in edge devices with conventional microprocessor hardware a slow and difficult task. In this paper, we propose to accelerate the computationally intensive GAN using memristive neural networks in analog domain. We present a fully analog hardware design of Deep Convolutional GAN (DCGAN) based on CMOS-memristive convolutional and deconvolutional networks simulated using 180nm CMOS technology.