Random resistive memory-based deep extreme point learning machine for unified visual processing

Visual sensors, including 3D light detection and ranging, neuromorphic dynamic vision sensor, and conventional frame cameras, are increasingly integrated into edge-side intelligent machines. However, their data are heterogeneous, causing complexity in system development. Moreover, conventional digital hardware is constrained by von Neumann bottleneck and the physical limit of transistor scaling. The computational demands of training ever-growing models further exacerbate these challenges. We propose a hardware-software co-designed random resistive memory-based deep extreme point learning machine. Data-wise, the multi-sensory data are unified as point set and processed universally. Software-wise, most weights are exempted from training. Hardware-wise, nanoscale resistive memory enables collocation of memory and processing, and leverages the inherent programming stochasticity for generating random weights. The co-design system is validated on 3D segmentation (ShapeNet), event recognition (DVS128 Gesture), and image classification (Fashion-MNIST) tasks, achieving accuracy comparable to conventional systems while delivering 6.78 × /21.04 × /15.79 × energy efficiency improvements and 70.12%/89.46%/85.61% training cost reductions.

Authors

Institutions

Publication Details

Journal
Nature Communications
Published
2025-01-23
DOI
https://doi.org/10.1038/s41467-025-56079-3
Citations
9
Primary Topic
Machine Learning and ELM
Type
article
Field-Weighted Citation Impact
22.33

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Random resistive memory-based deep extreme point learning machine for unified visual processing

Dashan Shang, Jia Chen, Hegan Chen, Hayden Kwok‐Hay So et al.
9 citations
Nature Communications
Machine Learning and ELM
22.33
article

Random resistive memory-based deep extreme point learning machine for unified visual processing

Dashan Shang, Jia Chen, Hegan Chen, Hayden Kwok‐Hay So, Peng Lin, Dingchen Wang, Woyu Zhang, Kwang‐Ting Cheng, Shaocong Wang, Zhongrui Wang, Yang Jiang, Qi Liu, Peng Dai, Ning Lin, Ming Liu, Yizhao Gao, Hao Jiang, Xiaojuan Qi, Yifei Yu, Xiaoxin Xu, Xumeng Zhang, Yue Zhang, Bo Wang, Yi Li
article en
9 citations

Abstract

Visual sensors, including 3D light detection and ranging, neuromorphic dynamic vision sensor, and conventional frame cameras, are increasingly integrated into edge-side intelligent machines. However, their data are heterogeneous, causing complexity in system development. Moreover, conventional digital hardware is constrained by von Neumann bottleneck and the physical limit of transistor scaling. The computational demands of training ever-growing models further exacerbate these challenges. We propose a hardware-software co-designed random resistive memory-based deep extreme point learning machine. Data-wise, the multi-sensory data are unified as point set and processed universally. Software-wise, most weights are exempted from training. Hardware-wise, nanoscale resistive memory enables collocation of memory and processing, and leverages the inherent programming stochasticity for generating random weights. The co-design system is validated on 3D segmentation (ShapeNet), event recognition (DVS128 Gesture), and image classification (Fashion-MNIST) tasks, achieving accuracy comparable to conventional systems while delivering 6.78 × /21.04 × /15.79 × energy efficiency improvements and 70.12%/89.46%/85.61% training cost reductions.

Nature CommunicationsVol. 16(1)
Zhejiang University of Science and Technology (CN), Chinese Academy of Sciences (CN), Hong Kong University of Science and Technology (HK), Fudan University (CN), Hong Kong Science and Technology Parks Corporation (HK), Southern University of Science and Technology (CN), Institute of Microelectronics (SG), Institute of Microelectronics (CN), University of Chinese Academy of Sciences (CN), University of Hong Kong (HK)
National Natural Science Foundation of China, Chinese Academy of Sciences, Innovation and Technology Fund
Openalex Percentile: Top 1%
Machine Learning and ELM
22.33
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.