Generative Adversarial network (GAn) requires extensive computing resources making its implementation in edge devices with conventional microprocessor hardware a slow and difficult, if not impossible task. in this paper, we propose to accelerate these intensive neural computations using memristive neural networks in analog domain. the implementation of Analog Memristive Deep convolutional GAn (AM-DcGAn) using Generator as deconvolutional and Discriminator as convolutional memristive neural network is presented. The system is simulated at circuit level with 1.7 million memristor devices taking into account memristor non-idealities, device and circuit parameters. the design is modular with crossbar arrays having a minimum average power consumption per neural computation of 47nW. The design exclusively uses the principles of neural network dropouts resulting in regularization and lowering the power consumption. the Spice level simulation of GAn is performed with 0.18 μm CMOS technology and WO x memristive devices with R ON = 40 kΩ and R OFF = 250 kΩ, threshold voltage 0.8 V and write voltage at 1.0 V. Intelligent near-sensor analog computing requires integration of neural co-processor unit next to the sensing unit. The analog memristive neuromorphic circuits 1 can integrate complex neural networks and learning systems to edge devices and sensors due to the advantages offered by memristors in area efficiency, non-volatility, programmability, high switching speeds, and low power requirements. Generative Adversarial Network (GAN) is a well known computationally complex neural network architecture for generating new patterns that requires significant computational resources in software implementations as well as large amount of data for training 2. This makes its implementation in edge devices with conventional microprocessor hardware a slow and difficult task. Recently, there have been several works proposing to accelerate GAN and implement the generative networks on FPGA 3,4 and digital CMOS circuits 5. These solutions have high power consumption and on-chip area for implementing within a edge device. The implementation of GAN on edge devices will eliminate the requirement of sending large amount of data collected by a sensor (e.g. in a camera) to a server for processing, which can speed up the GAN training on low power devices, where on-chip area, memory and power consumption is limited. The application of memristive devices for GAN can be a promising solution for near-sensor edge computing due to small on-chip area and low power consumption. Previously, memristive devices have been used for accelerating the vector-matrix multiplication operations in the neural networks and learning systems on hardware 6. Recently, a 128 × 64 reconfigurable hafnium oxide memristive crossbar has been tested for analogue vector-matrix multiplication with high device yield and high state retention for image processing applications 7. An integrated 128 × 64 1T1R crossbar array has been used in a Long-Short Term Memory (LSTM) network with...
This paper offers an introduction to the technological advances of image sensors designed using complementary metal-oxide-semiconductor (CMOS) processes along the last decades. We review some of those technological advances and examine potential disruptive growth directions for CMOS image sensors and proposed ways to achieve them. Those advances include breakthroughs on image quality such as resolution, capture speed, light sensitivity and color detection and advances on the computational imaging. The current trend is to push the innovation efforts even further as the market requires higher resolution, higher speed, lower power consumption and, mainly, lower cost sensors. Although CMOS image sensors are currently used in several different applications from consumer to defense to medical diagnosis, product differentiation is becoming both a requirement and a difficult goal for any image sensor manufacturer. The unique properties of CMOS process allows the integration of several signal processing techniques and are driving the impressive advancement of the computational imaging. With this paper, we offer a very comprehensive review of methods, techniques, designs and fabrication of CMOS image sensors that have impacted or might will impact the images sensor applications and markets.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.