Associative learning of a three-terminal memristor network for digits recognition

Imitating the associative intelligence of the biological brain is attractive but is poorly achieved in hardware because the complex tunable connection in neural networks is difficult to reproduce. We develop a circuit composed of a three-terminal memristor network to reproduce the biological conditi...

Full description

Saved in:
Bibliographic Details
Published in:Science China. Information sciences 2023-02, Vol.66 (2), p.122403, Article 122403
Main Authors: Ren, Yiming, Tian, Bobo, Yan, Mengge, Feng, Guangdi, Gao, Bin, Yue, Fangyu, Peng, Hui, Tang, Xiaodong, Zhu, Qiuxiang, Chu, Junhao, Duan, Chungang
Format: Article
Language:English
Subjects:
Associative memory
Biological activity
Brain
Circuits
Computer Science
Conditioning (learning)
Digital imaging
Electric fields
Electrodes
Energy consumption
Image classification
Information Systems and Communication Service
Learning
Memristors
Neural networks
Neurons
Object recognition
Research Paper
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Imitating the associative intelligence of the biological brain is attractive but is poorly achieved in hardware because the complex tunable connection in neural networks is difficult to reproduce. We develop a circuit composed of a three-terminal memristor network to reproduce the biological conditioning process artificially. The synaptic weight between co-firing neurons is strengthened simultaneously by generating a feedback signal from the integrate-and-fire neuron to the gate of the synaptic memristor. The network allows the multi-associative capacity of recalling more than one digit in one circuit. Both single and multi-associative learning for recalling digital images are achieved. Furthermore, all 10 digital images from “0” to “9” are successfully recalled in an associative network with such paralleling circuits. Assisted by this associative layer, a typical classification network effectively improves the recognition rate for fragmentary digital images. Our work sheds light on brain-inspired artificial associative memory and provides a strategy for applications, such as object recognition with partial features and similar scenes.
ISSN:1674-733X
1869-1919
DOI:10.1007/s11432-022-3503-4