2022 roadmap on neuromorphic devices and applications research in China

Abstract

The data throughput in the von Neumann architecture based computing system is limited by its separated processing and memory structure and the mismatching speed between the two units. As a result, it’s quite difficult to improve the energy efficiency in conventional computing system, especially for dealing with unstructured data. Meanwhile, artificial intelligence and robotics nowadays still behave poorly in autonomy, creativity and sociality, which has been considered as the unimaginable computational requirement for sensorimotor skills. These two plights have urged the imitation and replication of the biological systems in terms of computing, sensing, and even motoring. Hence, the so-called neuromorphic system has drawn world-wide attention in recent decade, which is aimed at addressing the aforementioned needs from the mimicking of neural system. The recent development on emerging memory devices, nanotechnologies, and materials science have provided an unprecedented opportunity for this aim. This roadmap profiles the potential trend in building neuromorphic systems from the view of Chinese scientists. The content of this roadmap will cover some core topics from multidisciplinary researchers including electronics, computer science, materials, physics, and so on. The perspectives and challenges are also discussed in partly, which may serve as the guidance for the pursuing of high energy-efficient and/or bio-realistic systems that can compute, sense, and act as our human beings. This will also give birth to some excited paradigm breakers and advanced technologies in a wide spectrum of areas.

A 0.8 V, 14.76 nVrms, Multiplexer-Based AFE for Wearable Devices Using 45 nm CMOS Techniques

“…They can now offer more individualized care and lower the possibility of difficulties during perfusion. It is possible to identify risks and treat medical diseases more quickly and effectively using wearables [5][6][7][8].…”

Bidirectional Invisible Photoresponse Implemented in a Traps Matrix-Combination toward Fully Optical Artificial Synapses

“…Therefore, to develop artificial neuromorphic computation, the successful implementation of synaptic functions in an artificial device would be an inevitable course. To do so, various two-terminal memristors and three-terminal transistors have been investigated, and remarkable progress has been achieved. − Yet, the mainstream stimulus to module the synaptic weight in those devices is electrical, which would face heat generation and bandwidth limitation along with the density increase. , In this regard, optical stimulus as an alternative operation method is more significant due to its potential benefits for low power consumption, high speed, and visual-perception neuromorphic devices. Especially, the artificial synapses that can be potentiated and depressed both by the optical stimuli, also known as the fully optical artificial synapses, would be the ideal device. − …”