Y
Yujie Wu
Researcher at Tsinghua University
Publications - 36
Citations - 2376
Yujie Wu is an academic researcher from Tsinghua University. The author has contributed to research in topics: Spiking neural network & Artificial neural network. The author has an hindex of 11, co-authored 27 publications receiving 983 citations. Previous affiliations of Yujie Wu include Lanzhou University.
Papers
More filters
Journal ArticleDOI
Towards artificial general intelligence with hybrid Tianjic chip architecture.
Jing Pei,Lei Deng,Sen Song,Sen Song,Mingguo Zhao,Youhui Zhang,Shuang Wu,Guanrui Wang,Zhe Zou,Zhenzhi Wu,Wei He,Feng Chen,Ning Deng,Si Wu,Yu Wang,Yujie Wu,Z. Yang,Cheng Ma,Guoqi Li,Wentao Han,Huanglong Li,Huaqiang Wu,Rong Zhao,Yuan Xie,Luping Shi +24 more
TL;DR: The Tianjic chip is presented, which integrates neuroscience-oriented and computer-science-oriented approaches to artificial general intelligence to provide a hybrid, synergistic platform and is expected to stimulate AGI development by paving the way to more generalized hardware platforms.
Journal ArticleDOI
Spatio-Temporal Backpropagation for Training High-Performance Spiking Neural Networks.
TL;DR: A spatio-temporal backpropagation (STBP) algorithm for training high-performance SNNs is proposed, which combines the layer-by-layer spatial domain (SD) and the timing-dependent temporal domain (TD), and does not require any additional complicated skill.
Journal ArticleDOI
Direct Training for Spiking Neural Networks: Faster, Larger, Better
TL;DR: In this paper, the authors propose a neuron normalization technique to adjust the neural selectivity and develop a direct learning algorithm for deep SNNs via narrowing the rate coding window and converting the leaky integrate-and-fire (LIF) model into an explicitly iterative version.
Posted Content
Direct Training for Spiking Neural Networks: Faster, Larger, Better
TL;DR: This work proposes a neuron normalization technique to adjust the neural selectivity and develops a direct learning algorithm for deep SNNs and presents a Pytorch-based implementation method towards the training of large-scale Snns.
Journal ArticleDOI
Rethinking the performance comparison between SNNS and ANNS.
Lei Deng,Lei Deng,Yujie Wu,Xing Hu,Ling Liang,Yufei Ding,Guoqi Li,Guangshe Zhao,Peng Li,Yuan Xie +9 more
TL;DR: This paper designs a series of contrast tests using different types of datasets (ANN-oriented and SNN-oriented), diverse processing models, signal conversion methods, and learning algorithms, and recommends the most suitable model for each scenario and highlights the urgent need to build a benchmarking framework for SNNs with broader tasks, datasets, and metrics.