Efficient and self-adaptive in-situ learning in multilayer memristor neural networks

By Can Li, Daniel Belkin, Yunning Li, Peng Yan, Miao Hu, Ning Ge, Hao Jiang, Eric Montgomery, Peng Lin, Zhongrui Wang and 7 more. Nature Communications, 2018

828 citations recorded by the source corpus.

Memristors with tunable resistance states are emerging building blocks of artificial neural networks. However, in situ learning on a large-scale multiple-layer memristor network has yet to be demonstrated because of challenges in device property engineering and circuit integration. Here we monolithically integrate hafnium oxide-based memristors with a foundry-made transistor array into a multiple-layer neural network. We experimentally demonstrate in situ learning capability and achieve competitive classification accuracy on a standard machine learning dataset, which further confirms that the training algorithm allows the network to adapt to hardware imperfections. Our simulation using the experimental parameters suggests that a larger network would further increase the classification accuracy. The memristor neural network is a promising hardware platform for artificial intelligence with high speed-energy efficiency. Memristor-based neural networks hold promise for neuromorphic computing, yet large-scale experimental execution remains difficult. Here, Xia et al. create a multi-layer memristor neural network with in-situ machine learning and achieve competitive image classification accuracy on a standard dataset.

Subfields: Education, Management Information Systems, Strategy and Management

View Paper: https://www.semanticscholar.org/paper/386fdc9b881df8a1c8acd9c4526f283e2ecdd1c5

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Shimeng Yu
2. Wenqiang Zhang
3. Bin Gao
4. Jianshi Tang
5. Peng Yao
6. Huaqiang Wu
7. J. Joshua Yang
8. He Qian

Citations in the corpus

• Large-Scale Optical Neural Networks based on Photoelectric Multiplication (2018, background): “Analog crossbar arrays based on CMOS gates [18] or memristors [19, 20] promise better performance, but as analog electronic devices, they suffer from calibration issues and limited accuracy [21].”
• Neuro-inspired computing chips (2020, background): “As a result, compared to defect-free simulation, the hardware implementation would show a lower computing accuracy 38 .”
• Fully hardware-implemented memristor convolutional neural network (2020, methodology): “However, previous memristor-based demonstrations relied on a single array 4,24–26 , mainly because of the challenge of producing highly repeatable arrays.”