AXAnqin Xiao

Anqin Xiao

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Anqin Xiao has a total of 16 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • An Always-On Event-Triggered DVS Fall Detection Processor With Precision-Adaptive Inference in 40-nm CMOS

    by Ziyi Yang, Yushi Wang, Jinqiao Yang, Quanshu Yan, Anqin Xiao, Li-Rong Zheng, Zhuo Zou

    Fall detection is critical in elderly care, where always-on, low-power monitoring is essential due to multi-node, battery-powered deployment across complex home environments. This work presents an event-triggered fall detection chip with precision-adaptive inference, optimized for always-on real-time processing of Dynamic Vision Sensor (DVS) data. The proposed chip features an end-to-end architecture that directly accepts raw address event representation (AER) input and integrates a preprocessing module and a precision-adaptive spiking neural network (SNN) into a unified hardware framework. The proposed chip dynamically adjusts inference precision based on real-time activity levels: low-risk actions trigger low-precision inference with 4-bit weights, while high-risk movements switch to high-precision 8-bit inference for accurate fall detection. Additionally, the chip incorporates a generic memory-free spatiotemporal denoising architecture which contributes to at least a 1% improvement in accuracy, while a timestep skipping strategy further reduces energy and latency by nearly 20% during few-event periods without sacrificing performance for fall detection. Fabricated in 40-nm CMOS, the chip occupies 0.88 mm2, and achieves the best energy efficiency of 2.2 pJ/SOP at 20 MHz. This processor achieves 3.9 pJ per event on the DVSGesture128 dataset, demonstrating state-of-the-art performance in event-level processing efficiency. In the typical home-activity scenario, the event-triggered mode achieves a 64.8% improvement in battery life compared to the fixed 8-bit precision configuration.

  • A 40-nm Sub-mJ/Transfer HDC-SNN Hybrid Processor Enabling On-Chip Few-Shot Transfer Learning for IoT Applications

    by Anqin Xiao, Jinqiao Yang, Wanlin Yang, Xin Zhang, Yuhan He, Ziyi Yang, Li-Rong Zheng, Zhuo Zou

    This work presents a brain-inspired processor that combines Hyperdimensional Computing (HDC) and Spiking Neural Network (SNN), or HDC-SNN hybrid, to enable on-chip few-shot transfer learning (FSTL) for IoT applications. Such an HDC-SNN hybrid architecture utilizes SNN for efficient feature extraction to suppress the size of the vector dimension, thus mitigating intensive operations and the memory footprint for HDC. It also leverages the few-shot and single-pass learning capability of HDC, eliminating the need for abundant labeled samples and training epochs. This processor utilizes a task-agnostic spiking HDC encoder to generate spatio-temporal feature vectors, followed by an on-chip learning HDC classifier. Furthermore, the implementation of on-chip learning uses the schemes of weight access from destination-neuron with memory bank (WAD-MB) and batch-by-batch gradient computation (BGC), achieving a significant improvement on training latency and cache size. This design is fabricated in a 40-nm CMOS technology with a peak efficiency of sub-mJ/transfer (mJ/class and mJ/patient by on-chip FSTL) at 0.72V and 65MHz, occupying a core area of 1.56 mm${}^{2}$. For typical neuromorphic datasets, this processor achieves a 1.6-35x improvement in training energy per class and a 3.5-52x reduction in training latency per sample, compared to state-of-the-art processors. For patient-specific and class-incremental scenarios, it achieves an accuracy of over 96% in both ECG arrhythmia detection and bearing anomaly detection. Specifically, it requires only 2-minute training samples for a new patient with 0.1 mJ energy, achieving a 4.5× improvement in energy efficiency; it employs 3-shot learning for a new class with only 0.3 mJ energy, reducing training epochs by over 100×.


  • CAMPRO: A CAM-Based Processing-in-Memory Processor for Hyperdimensional Computing

    by Yuhan He, Tianxi Hu, Anqin Xiao, Fanxi Yang, Hengtan Zhang, Li-Rong Zheng, Zhuo Zou

    This work introduces CAMPRO, a Content Addressable Memory (CAM)-based Processing-In-Memory (PIM) processor customized for Hyperdimensional Computing (HDC). CAMPRO leverages a 6T Split Word Lines (SWL) cell structure for its CAM, enabling efficient column-wise search for ultra-wide Hypervector (HV) storage and an optimized associative PIM architecture tailored to HDC operations, significantly enhancing energy efficiency. The four key operators of HDC, binding, bundling, permutation, and similarity, are mapped to the proposed architecture. CAMPRO enhances operational parallelism via approximate bundling and employs a hierarchical permutation method to mitigate the gap in flexible shift support within CAM-based PIM architecture. The fine grained pipelined operations boost processing efficiency and dynamically reclaim memory space to support larger models. The Two-Phase Bit Pruning (TPBP) strategy prunes redundant bits in class HVs across two computing stages to eliminate unnecessary computations, reducing operation counts by 73.6% and energy consumption by 65.2% while maintaining query precision. Simulated in a 22 nm CMOS process, CAMPRO occupies 1.13 mm2 and consumes 0.99 mW at 200 MHz. CAMPRO demonstrates robust versatility and scalability across five datasets, including MUTAG, CIFAR10, MNIST, language classification, and EMG gesture recognition, using diverse encoding schemes. It achieves excellent energy efficiency and low latency from small to large-scale datasets. In language classification, it reduces inference energy by 99.2% compared to the similiar work. For EMG gesture recognition, it improves training and inference energy efficiency by 2.6x and 6.7x, and reduce inference latency by 73x compared to related works. On MNIST, it enhances energy efficiency by 11.3x and latency by 1.6x to the prior work, making it an efficient Artificial Intelligence of Things (AIoT) solution.


  • A 0.66-mm 2 0.49 pJ/SOP SNN Processor With Temporal-Spatial Post-Neuron-Processing and Model-Adaptive Crossbar in 40-nm CMOS

    by Jinqiao Yang, Zikai Zhu, Haoming Chu, Anqin Xiao, Yuxiang Huan, Lirong Zheng, Zhuo Zou

    This paper presents a Spiking Neural Network (SNN) processor specifically designed to overcome the limitations of existing parallel architectures in maintaining high energy efficiency and model adaptability in a compact area footprint for Artificial Intelligence of Things (AIoT). This is achieved through two key design features: a Temporal-Spatial Post-Neuron Processing (PoNP) scheme that efficiently reuses membrane potential, maximizes parallelism, and reduces memory bank requirements; and a Model-Adaptive Crossbar design with preconfigured parameters and a dynamic switching mechanism enables processing of various SNN models through operation orchestration without efficiency degradation. Using an 8-way parallel pipeline design, the processor achieves a throughput of 128 Synaptic Operations (SOPs) per cycle, resulting in a 2.8× enhancement in energy efficiency. Fabricated in a 40-nm CMOS process, the chip occupies a compact core area of 0.66 mm2. It achieves a power consumption of 6.26 mW, an energy efficiency of 0.49 pJ/SOP, and a throughput of 12.8 GSOPS/s at 0.75 V, 100 MHz. The chip is evaluated using typical spatial, temporal, and temporal-spatial datasets, including MIT-BIH, MNIST, N-MNIST, NavGesture, and SHD. These results demonstrate that our chip achieves best-in-class in terms of energy efficiency and latency compared to state-of-the-art architectures.