Houpeng Chen

Memory-Based Computing for Resource-Constrained Embedded Device Applications: A Case Study

Weibang Dai, Xiaogang Chen, Sannian Song, Houpeng Chen et autres

cn (code pays fourni par la source)

Lookup Table-based Computing: A Survey from Software Implementations to Hardware Architectures

Weibang Dai, Xiaogang Chen, Houpeng Chen, Sannian Song et autres

For decades, memory-based computation has been overshadowed by processor-centric paradigms. However, memory-based computation offers distinct advantages, including high-speed operation and energy efficiency. As a representative and powerful type of memory-based computation, lookup table (LUT)-based computing has seen a resurgence in interest. Recent …

cn (code pays fourni par la source)

Bayesian Neural Network Realization by Exploiting Random Noise and Mitigating the Impact of Conductance Drift of PCM

Yu Lei, Li Xie, Qian Wang, Yonghui Zheng et autres

Abstract Bayesian neural networks (BNNs) provide inference with uncertainty prediction, which is critical for safety‐sensitive applications such as autonomous driving and medical diagnosis. However, conventional implementations relying on Gaussian random number generators incur significant area and power overheads. In this work, the …

cn (code pays fourni par la source)

Revisiting a classic form of memory-centric computing—lookup table

Weibang Dai, Xiaogang Chen, Sannian Song, Houpeng Chen et autres

cn (code pays fourni par la source)

Memristive In‐Memory Object Detection with 128 Mb C‐Doped Ge 2 Sb 2 Te 5 PCM Chip

Chenchen Xie, Yuqi Li, Longhao Yan, Sannian Song et autres

Object detection, as a fundamental task in computer vision, mainly performs the classification and localization of objects in images or videos. However, traditional edge computing platforms fall short of meeting the demands for state-of-the-art object detection model size and computing power. Here, …

cn (code pays fourni par la source)

Snoring Sounds Classification of OSAHS Patients Based on Model Fusion

Y. X. Luo, Jianxin Peng, Li Ding, Yikai Zhang et autres

Obstructive sleep apnea hypopnea syndrome (OSAHS) is a prevalent and detrimental chronic condition. The conventional diagnostic approach for OSAHS is intricate and costly. Snoring is one of the most typical and easily obtained symptom of OSAHS patients. In this study, a series …

cn (code pays fourni par la source)

Phase change memory programming circuit with improved speed

Xinyu Yang, Yu Lei, Qiuyao Yu, Qian Wang et autres

Abstract Phase change memory (PCM) is considered one of the most promising next-generation non-volatile memory types for storage-class memory due to its many advantages, including ultrafast programming, long data retention, high storage density, low power consumption, and compatibility with standard CMOS processes. …

cn (code pays fourni par la source)

Research and Improvement of Muller C Element

Zhizhi Chen, Qian Wang, Houpeng Chen, Xi Li et autres

ABSTRACT The basic structure of conventional Muller C element is studied and the output errors caused by node parasitic capacitors are analysed in this letter. In order to avoid such errors, an improved C element with two inverted ratio MOS transistors added …

cn (code pays fourni par la source)

MSFANC: A Case Study of Memory-Based Computing for Wearable Device Applications

Weibang Dai, Xiaogang Chen, Houpeng Chen, Sannian Song et autres

This letter emphasizes memory-based computing’s potential in enhancing efficiency for wearable devices with limited resources, focusing on active noise control (ANC) in wireless earbuds. Our proposed memory-based selective fixed-filter ANC (MSFANC) scheme reduces power consumption and delay through lookup table (LUT) computation …

cn, de (code pays fourni par la source)

A Robust Low‐Power Power‐On‐Reset Circuit With Dual Threshold Method

Luchang He, Chenchen Xie, Qingyu Wu, Liping Xu et autres

ABSTRACT In this paper, a robust low‐power power‐on‐reset (POR) circuit with dual threshold method is proposed. The current‐based circuit exhibits good robustness with respect to process, voltage, temperature, and supply ramp variations. In contrast to conventional delay‐based pulse generation approaches, a dual …

cn (code pays fourni par la source)

Hybrid Computing Architecture Based on Analog Phase-Change Memory Chips for Deep Neural Network Training

Xiaogang Chen, Tao Hong, Weibang Dai, Chengcai Tu et autres

Deep neural networks (DNNs) have revolutionized fields like image recognition and natural language processing but face limitations with traditional von Neumann architectures due to high energy consumption and limited computing speed. We propose a hybrid architecture for DNN training combining a digital …

cn (code pays fourni par la source)

A Low-Cost Quadruple-Node-Upsets Resilient Latch Design

Luchang He, Chenchen Xie, Qingyu Wu, Siqiu Xu et autres

In this article, a low-cost quadruple-node-upsets resilient latch (LCQRL) design is proposed. To meet the high-reliability demands of safety-critical applications, the latch integrates nine soft-error-interceptive modules (SIMs) to form robust feedback loops, ensuring complete resilience to quadruple-node upsets (QNUs). Each Sim comprises …

cn (code pays fourni par la source)