Key Technologies and Challenges of Memory Resistors and Brain like Chips in Improving Computing Power

Authors

  • Wenhan Wang

DOI:

https://doi.org/10.54097/brrj7e17

Keywords:

Memristors, Parallelism, Chips, Neural network, Artificial intelligence.

Abstract

This article explores the cutting-edge applications of brain like chips and memristors in the fields of artificial intelligence and computer science. Brain like chips, imitating the computational model of brain neural networks, provide new hardware support for machine learning and deep learning with unique parallel processing capabilities and efficient energy consumption ratio. Memristors, as an emerging type of non-volatile memory, have great potential in information storage and processing as resistance can change with changes in passing current and voltage. This article first outlines the basic principles and characteristics of brain like chips and memristors, then analyzes application prospects in the fields of computational science and neuroscience, and finally discusses the current challenges and future development trends. This article aims to provide a comprehensive perspective on the latest developments in brain like chips and memristors for researchers in related fields, and promote the deep integration and application of these two technologies in the field of artificial intelligence.

Downloads

Download data is not yet available.

References

Xu K., “Design and research of high-energy efficient deep neural network acceleration chips [D]”, Xi'an University of Electronic Science and Technology, 2022, 1-10 (2022). (In Chinese)

Xia, Q. and Yang J.J., “Memristive crossbar arrays for brain-inspired computing”, Nat. Mater. 18, 309–323 (2019).

Kumar, S., Wang, X. and Strachan, J.P., “Dynamical memristors for higher-complexity neuromorphic computing”, Nat Rev Mater 7, 575–591 (2022).

Zhao R.J., Fang C. and Xu M.S., “Development Status and Prospects of Artificial Intelligence Chip Industry [J]”, Economic Journal, 2022(11), 75-81 (2022). (In Chinese)

Ambrogio, S., Narayanan, P., Okazaki, A., “An analog-AI chip for energy-efficient speech recognition and transcription”, Nature 620, 768–775 (2023).

Sun Z.Y., Xiao S.Y. and Shen Q., “Design of Satellite Intelligence Platform Based on Heterogeneous Fusion Brain like Chips [J]”, Aerospace Standardization, 2022, (01), 40-43 (2022). (In Chinese)

Zhang F., Zhai J.D. and Chen Z., “Performance Analysis, Optimization, and Application Review for Heterogeneous Fusion Processors [J]”, Journal of Software, 2020, 31(08), 2603-2624 (2020). (In Chinese)

Chen C.L. , Luo C.H. and Liu S. , “Review of research status on memristor based brain computing chips [J]”, Journal of National University of Defense Technology, 2023,45(01), 1-14 (2023). (In Chinese)

Tang C.F. and Hu W., “Low latency and low energy consumption novel sensing amplifier for memory resistor array in memory computing [J/OL]”, Microelectronics and Computers, 2024, (02), 58-66(2024). (In Chinese)

Chen, Z., Lin, Z. and Yang, J., “Cross-layer transmission realized by light-emitting memristor for constructing ultra-deep neural network with transfer learning ability”, Nat Commun 15, 19-30 (2024).

Downloads

Published

26-06-2024