Tags

Type your tag names separated by a space and hit enter

Power-efficient neural network with artificial dendrites.
Nat Nanotechnol. 2020 Jun 29 [Online ahead of print]NN

Abstract

In the nervous system, dendrites, branches of neurons that transmit signals between synapses and soma, play a critical role in processing functions, such as nonlinear integration of postsynaptic signals. The lack of these critical functions in artificial neural networks compromises their performance, for example in terms of flexibility, energy efficiency and the ability to handle complex tasks. Here, by developing artificial dendrites, we experimentally demonstrate a complete neural network fully integrated with synapses, dendrites and soma, implemented using scalable memristor devices. We perform a digit recognition task and simulate a multilayer network using experimentally derived device characteristics. The power consumption is more than three orders of magnitude lower than that of a central processing unit and 70 times lower than that of a typical application-specific integrated circuit chip. This network, equipped with functional dendrites, shows the potential of substantial overall performance improvement, for example by extracting critical information from a noisy background with significantly reduced power consumption and enhanced accuracy.

Authors+Show Affiliations

Institute of Microelectronics, Beijing Innovation Center for Future Chips (ICFC), Tsinghua University, Beijing, China.Institute of Microelectronics, Beijing Innovation Center for Future Chips (ICFC), Tsinghua University, Beijing, China. Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China.Institute of Microelectronics, Beijing Innovation Center for Future Chips (ICFC), Tsinghua University, Beijing, China.Institute of Microelectronics, Beijing Innovation Center for Future Chips (ICFC), Tsinghua University, Beijing, China. Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China.Department of Electrical and Computer Engineering, University of Massachusetts, Amherst, MA, USA.Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China.Institute of Microelectronics, Beijing Innovation Center for Future Chips (ICFC), Tsinghua University, Beijing, China.Institute of Microelectronics, Beijing Innovation Center for Future Chips (ICFC), Tsinghua University, Beijing, China.Institute of Microelectronics, Beijing Innovation Center for Future Chips (ICFC), Tsinghua University, Beijing, China.Institute of Microelectronics, Beijing Innovation Center for Future Chips (ICFC), Tsinghua University, Beijing, China. Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China.Department of Electrical and Computer Engineering, University of California at Santa Barbara, Santa Barbara, CA, USA.Department of Electrical and Computer Engineering, University of California at Santa Barbara, Santa Barbara, CA, USA. Alibaba DAMO Academy, Hangzhou, China.Institute of Microelectronics, Beijing Innovation Center for Future Chips (ICFC), Tsinghua University, Beijing, China. Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China.Institute of Microelectronics, Beijing Innovation Center for Future Chips (ICFC), Tsinghua University, Beijing, China. wuhq@tsinghua.edu.cn. Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University, Beijing, China. wuhq@tsinghua.edu.cn.

Pub Type(s)

Journal Article

Language

eng

PubMed ID

32601451

Citation

Li, Xinyi, et al. "Power-efficient Neural Network With Artificial Dendrites." Nature Nanotechnology, 2020.
Li X, Tang J, Zhang Q, et al. Power-efficient neural network with artificial dendrites. Nat Nanotechnol. 2020.
Li, X., Tang, J., Zhang, Q., Gao, B., Yang, J. J., Song, S., Wu, W., Zhang, W., Yao, P., Deng, N., Deng, L., Xie, Y., Qian, H., & Wu, H. (2020). Power-efficient neural network with artificial dendrites. Nature Nanotechnology. https://doi.org/10.1038/s41565-020-0722-5
Li X, et al. Power-efficient Neural Network With Artificial Dendrites. Nat Nanotechnol. 2020 Jun 29; PubMed PMID: 32601451.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Power-efficient neural network with artificial dendrites. AU - Li,Xinyi, AU - Tang,Jianshi, AU - Zhang,Qingtian, AU - Gao,Bin, AU - Yang,J Joshua, AU - Song,Sen, AU - Wu,Wei, AU - Zhang,Wenqiang, AU - Yao,Peng, AU - Deng,Ning, AU - Deng,Lei, AU - Xie,Yuan, AU - Qian,He, AU - Wu,Huaqiang, Y1 - 2020/06/29/ PY - 2018/09/15/received PY - 2020/06/01/accepted PY - 2020/7/1/entrez JF - Nature nanotechnology JO - Nat Nanotechnol N2 - In the nervous system, dendrites, branches of neurons that transmit signals between synapses and soma, play a critical role in processing functions, such as nonlinear integration of postsynaptic signals. The lack of these critical functions in artificial neural networks compromises their performance, for example in terms of flexibility, energy efficiency and the ability to handle complex tasks. Here, by developing artificial dendrites, we experimentally demonstrate a complete neural network fully integrated with synapses, dendrites and soma, implemented using scalable memristor devices. We perform a digit recognition task and simulate a multilayer network using experimentally derived device characteristics. The power consumption is more than three orders of magnitude lower than that of a central processing unit and 70 times lower than that of a typical application-specific integrated circuit chip. This network, equipped with functional dendrites, shows the potential of substantial overall performance improvement, for example by extracting critical information from a noisy background with significantly reduced power consumption and enhanced accuracy. SN - 1748-3395 UR - https://www.unboundmedicine.com/medline/citation/32601451/Power-efficient_neural_network_with_artificial_dendrites DB - PRIME DP - Unbound Medicine ER -
Try the Free App:
Prime PubMed app for iOS iPhone iPad
Prime PubMed app for Android
Prime PubMed is provided
free to individuals by:
Unbound Medicine.