ApGAN: Approximate GAN for Robust Low Energy Learning From Imprecise Components
ApGAN: Approximate GAN for Robust Low Energy Learning From Imprecise Components
复制标题
DOI：
10.1109/tc.2019.2949042
复制
发表时间：
2020-03-01
影响因子：
3.7
通讯作者：
DeMara, Ronald F.
中科院分区：
文献类型：
--
作者：
Roohi, Arman;Sheikhfaal, Shadi;DeMara, Ronald F.
生成对抗网络（Generative Adversarial Network，GAN）是一种对抗性学习方法，通过减轻对大量标记数据集的需求来增强传统的深度学习方法。然而，GAN训练可能是计算密集型的，限制了其在资源有限的边缘设备中的可行性。在本文中，我们提出了一种近似GAN（ApGAN），用于从算法和硬件实现的角度加速GAN。首先，受二进制模式特征提取方法沿着与二进制表示熵的启发，通过将生成器和卷积模型内的层的特定部分的权重二进制化来修改现有的深度卷积GAN（DCGAN）算法。进一步减少存储和计算资源是通过利用一种新的硬件可配置的内存中添加方案，它可以在精确和近似模式下操作。最后，开发了一个基于忆阻器的ApGAN内存处理加速器。评估ApGAN加速器在不同数据集上的性能，如Fashion-MNIST，CIFAR-10，STL-10和celeb-A，并与最近的GAN加速器设计进行比较。ApGAN加速器的Inception Score（IS）与基线GAN几乎相同，与基线GPU平台相比，ApGAN加速器可以将能效提高28.6倍，实现35倍的加速。此外，它还显示出比CMOS ASIC加速器高2.5倍和5.8倍的能效和加速比，但IS减少了11%。
A Generative Adversarial Network (GAN) is an adversarial learning approach which empowers conventional deep learning methods by alleviating the demands of massive labeled datasets. However, GAN training can be computationally-intensive limiting its feasibility in resource-limited edge devices. In this paper, we propose an approximate GAN (ApGAN) for accelerating GANs from both algorithm and hardware implementation perspectives. First, inspired by the binary pattern feature extraction method along with binarized representation entropy, the existing Deep Convolutional GAN (DCGAN) algorithm is modified by binarizing the weights for a specific portion of layers within both the generator and discriminator models. Further reduction in storage and computation resources is achieved by leveraging a novel hardware-configurable in-memory addition scheme, which can operate in the accurate and approximate modes. Finally, a memristor-based processing-in-memory accelerator for ApGAN is developed. The performance of the ApGAN accelerator on different data-sets such as Fashion-MNIST, CIFAR-10, STL-10, and celeb-A is evaluated and compared with recent GAN accelerator designs. With almost the same Inception Score (IS) to the baseline GAN, the ApGAN accelerator can increase the energy-efficiency by 28.6x achieving 35-fold speedup compared with a baseline GPU platform. Additionally, it shows 2.5x and 5.8x higher energy-efficiency and speedup over CMOS-ASIC accelerator subject to an 11 percent reduction in IS.