Comprehensive Evaluation of Neuromorphic Computing

Computation in its many forms is the engine that fuels our modern civilization. Modern computation based on the von Neumann architecture has allowed, until now, the development of continuous improvements, as predicted by Moore’s law. However, computation using current architectures and materials will inevitably within the next 10 years reach a limit because of fundamental scientific reasons. The development of novel functional materials and devices incorporated into unique architectures will allow a revolutionary technological leap toward the implementation of a fully “neuromorphic” computer. Computers have become essential to all aspects of Modern life from process controls, engineering, and science to entertainment and communications and are omnipresent all over the globe. Currently, about 5–15% of the world’s energy is spent in some form of data manipulation, transmission, or processing. In the early 1990s, researchers began to investigate the idea of “neuromorphic” computing [15-18]. Nervous system--‐ inspired analog computing devices were envisioned to be a million times more power efficient than devices being developed at that time. While conventional computational devices had achieved notable feats, they failed in some of the most basic tasks that biological systems have mastered, such as speech and image recognition. Hence the idea that taking cues from biology might lead to fundamental improvements in computational capabilities. Since that time, Researchers have said witnessed unprecedented progress in CMOS technology that has resulted in systems that are significantly more power efficient than imagined. Systems have been mass produced with over 5 billion transistors per die, and feature sizes are now approaching 10 nm. These advances made possible a revolution in parallel computing. Today, parallel computing is commonplace with hundreds of millions of cell phones and personal computers containing multiple processors, and the largest supercomputers having CPU counts in the millions. “Machine learning” software is used to tackle problems with complex and noisy datasets that cannot be solved with conventional “non-learning” algorithms [19,20]. Considerable progress has been made recently in this area using parallel processors. These methods are proving so effective that all major Internet and computing companies now have “deep learning” the branch of machine learning that builds tools based on deep (multilayer) neural networks research opus. Moreover, most major Abstract: Due to technological advancements in the field computing and networking as well, neuromorphic computing has been evolving more and more fast. Advance technologies such as neural and peripheral nerves in human body are growing explosively. If this trend goes on the computing networks congestion will increase and it would be difficult to supply large services to the needy patients. To go on with the flow without any traffic problems neuromorphic computing is the best solution. This paper aims to discuss evaluate address the methods to assess various neuromorphic computing system. Here authors are discussing resistive switching and its properties, gallium doped ZnO and behaviour of memristive resistors which are playing crucial role in neuromorphic computing. It’s an attempt to address the new systems and their role as well as various issues associated with it which are contributing the computing domain.