Search

Your search keyword '"Li, Yanchen"' showing total 346 results
Start Over Author "Li, Yanchen"
346 results on '"Li, Yanchen"'

1. Towards Scalable GPU-Accelerated SNN Training via Temporal Fusion

Author

Li, Yanchen, Li, Jiachun, Sun, Kebin, Leng, Luziwei, and Cheng, Ran

Subjects
Computer Science - Artificial Intelligence, Computer Science - Distributed, Parallel, and Cluster Computing
Abstract

Drawing on the intricate structures of the brain, Spiking Neural Networks (SNNs) emerge as a transformative development in artificial intelligence, closely emulating the complex dynamics of biological neural networks. While SNNs show promising efficiency on specialized sparse-computational hardware, their practical training often relies on conventional GPUs. This reliance frequently leads to extended computation times when contrasted with traditional Artificial Neural Networks (ANNs), presenting significant hurdles for advancing SNN research. To navigate this challenge, we present a novel temporal fusion method, specifically designed to expedite the propagation dynamics of SNNs on GPU platforms, which serves as an enhancement to the current significant approaches for handling deep learning tasks with SNNs. This method underwent thorough validation through extensive experiments in both authentic training scenarios and idealized conditions, confirming its efficacy and adaptability for single and multi-GPU systems. Benchmarked against various existing SNN libraries/implementations, our method achieved accelerations ranging from $5\times$ to $40\times$ on NVIDIA A100 GPUs. Publicly available experimental codes can be found at https://github.com/EMI-Group/snn-temporal-fusion., Comment: International Conference on Artificial Neural Networks (ICANN) 2024

Published
2024

2. Automotive Object Detection via Learning Sparse Events by Spiking Neurons

Author

Zhang, Hu, Li, Yanchen, Leng, Luziwei, Che, Kaiwei, Liu, Qian, Guo, Qinghai, Liao, Jianxing, and Cheng, Ran

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Event-based sensors, distinguished by their high temporal resolution of 1 $\mathrm{\mu}\text{s}$ and a dynamic range of 120 $\text{dB}$, stand out as ideal tools for deployment in fast-paced settings like vehicles and drones. Traditional object detection techniques that utilize Artificial Neural Networks (ANNs) face challenges due to the sparse and asynchronous nature of the events these sensors capture. In contrast, Spiking Neural Networks (SNNs) offer a promising alternative, providing a temporal representation that is inherently aligned with event-based data. This paper explores the unique membrane potential dynamics of SNNs and their ability to modulate sparse events. We introduce an innovative spike-triggered adaptive threshold mechanism designed for stable training. Building on these insights, we present a specialized spiking feature pyramid network (SpikeFPN) optimized for automotive event-based object detection. Comprehensive evaluations demonstrate that SpikeFPN surpasses both traditional SNNs and advanced ANNs enhanced with attention mechanisms. Evidently, SpikeFPN achieves a mean Average Precision (mAP) of 0.477 on the GEN1 Automotive Detection (GAD) benchmark dataset, marking significant increases over the selected SNN baselines. Moreover, the efficient design of SpikeFPN ensures robust performance while optimizing computational resources, attributed to its innate sparse computation capabilities. Source codes are publicly accessible at https://github.com/EMI-Group/spikefpn., Comment: IEEE Transactions on Cognitive and Developmental Systems

Published
2023
Full Text
View/download PDF

6. A One-Shot Reparameterization Method for Reducing the Loss of Tile Pruning on DNNs

Author

Li, Yanchen, Ai, Qingzhong, and Ino, Fumihiko

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Machine Learning
Abstract

Recently, tile pruning has been widely studied to accelerate the inference of deep neural networks (DNNs). However, we found that the loss due to tile pruning, which can eliminate important elements together with unimportant elements, is large on trained DNNs. In this study, we propose a one-shot reparameterization method, called TileTrans, to reduce the loss of tile pruning. Specifically, we repermute the rows or columns of the weight matrix such that the model architecture can be kept unchanged after reparameterization. This repermutation realizes the reparameterization of the DNN model without any retraining. The proposed reparameterization method combines important elements into the same tile; thus, preserving the important elements after the tile pruning. Furthermore, TileTrans can be seamlessly integrated into existing tile pruning methods because it is a pre-processing method executed before pruning, which is orthogonal to most existing methods. The experimental results demonstrate that our method is essential in reducing the loss of tile pruning on DNNs. Specifically, the accuracy is improved by up to 17% for AlexNet while 5% for ResNet-34, where both models are pre-trained on ImageNet., Comment: Presented at IJCNN 2022, oral

Published
2022

40. Biodecolorization and Biodegradation of Sulfur Black by the Strain Aspergillus sp. DS-28.

Author

Guan, Zhipeng, Wang, Yating, Chen, Wentao, Li, Yanchen, Yue, Wenlong, and Cai, Zhiqiang

Subjects
LIQUID chromatography-mass spectrometry, HIGH performance liquid chromatography, SIZE reduction of materials, INFRARED spectroscopy, WASTE management
Abstract

The textile industry significantly contributes to environmental pollution through its use of synthetic dyes, especially sulfur black, known for its toxicity and resistance to degradation. This research focuses on a fungal strain, Aspergillus sp. strain DS-28, isolated from activated sludge, which exhibits an exceptional ability to biodegrade sulfur black dye. This study systematically assessed the biodegradation capacity of this strain through a series of experiments conducted over a 7-day period. Analytical techniques including high-performance liquid chromatography time-of-flight mass spectrometry (HPLC-TOF/MS), scanning electron microscopy (SEM), X-ray diffraction (XRD), and Fourier-transform infrared spectroscopy (FTIR) were employed to monitor the degradation process. SEM showed a significant reduction in particle size, with surfaces becoming smoother and flatter post treatment. XRD indicated a decrease in the intensity of several chemical bonds, and FTIR analysis demonstrated the enhanced vibrational absorption peaks of benzene ring bonds, with the disappearance of -C-S- and -C-S-S-C- groups. The results demonstrate that Aspergillus sp. DS-28 degrades sulfur black by initiating the oxidative breakdown of its complex structures into simpler forms. This study not only elucidates the biodegradation pathway facilitated by Aspergillus sp. DS-28, but also highlights its potential application in developing eco-friendly waste management strategies for treating dye-contaminated wastewater. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

45. Application of 3D Animation Technology in Roaming Visualization of Anhui Museum

Author

Liu, Gang, Li, Yanchen, Kacprzyk, Janusz, Series Editor, Pal, Nikhil R., Advisory Editor, Bello Perez, Rafael, Advisory Editor, Corchado, Emilio S., Advisory Editor, Hagras, Hani, Advisory Editor, Kóczy, László T., Advisory Editor, Kreinovich, Vladik, Advisory Editor, Lin, Chin-Teng, Advisory Editor, Lu, Jie, Advisory Editor, Melin, Patricia, Advisory Editor, Nedjah, Nadia, Advisory Editor, Nguyen, Ngoc Thanh, Advisory Editor, Wang, Jun, Advisory Editor, Abawajy, Jemal H., editor, Choo, Kim-Kwang Raymond, editor, Islam, Rafiqul, editor, Xu, Zheng, editor, and Atiquzzaman, Mohammed, editor

Published
2020
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results