S
Sicheng Li
Researcher at Hewlett-Packard
Publications - 29
Citations - 572
Sicheng Li is an academic researcher from Hewlett-Packard. The author has contributed to research in topics: Image segmentation & Electronics. The author has an hindex of 10, co-authored 26 publications receiving 383 citations. Previous affiliations of Sicheng Li include New York University & University of Pittsburgh.
Papers
More filters
Journal ArticleDOI
Low-voltage high-performance flexible digital and analog circuits based on ultrahigh-purity semiconducting carbon nanotubes.
Ting Lei,Leilai Shao,Yu-Qing Zheng,Gregory Pitner,Guanhua Fang,Chenxin Zhu,Sicheng Li,Raymond G. Beausoleil,H-S Philip Wong,Tsung-Ching Huang,Kwang-Ting Cheng,Kwang-Ting Cheng,Zhenan Bao +12 more
TL;DR: Low-voltage and high-performance digital and analog CNT TFT circuits based on high-yield and ultrahigh purity polymer-sorted semiconducting CNTs and the first tunable-gain amplifier with 1,000 gain at 20 kHz are reported.
Proceedings ArticleDOI
FPGA Acceleration of Recurrent Neural Network Based Language Model
TL;DR: This work presents an FPGA implementation framework for RNNLM training acceleration and improves the parallelism of RNN training scheme and reduces the computing resource requirement for computation efficiency enhancement.
Posted Content
LotteryFL: Personalized and Communication-Efficient Federated Learning with Lottery Ticket Hypothesis on Non-IID Datasets.
TL;DR: This work proposes LotteryFL -- a personalized and communication-efficient federated learning framework via exploiting the Lottery Ticket hypothesis, and constructs non-IID datasets based on MNIST, CIFAR-10 and EMNIST by taking feature distribution skew, label distribution skew and quantity skew into consideration.
Posted Content
ShiftAddNet: A Hardware-Inspired Deep Network
Haoran You,Xiaohan Chen,Yongan Zhang,Chaojian Li,Sicheng Li,Zihao Liu,Zhangyang Wang,Yingyan Lin +7 more
TL;DR: This paper presented ShiftAddNet, whose main inspiration is drawn from a common practice in energy-efficient hardware implementation, that is, multiplication can be instead performed with additions and logical bit-shifts, yielding a new type of deep network that involves only bit-shift and additive weight layers.
Journal ArticleDOI
Neuromorphic computing's yesterday, today, and tomorrow an evolutional view
Yi Chen,Hai Li,Chunpeng Wu,Chang Song,Sicheng Li,Chuhan Min,Hsin-Pai Cheng,Wei Wen,Xiaoxiao Liu +8 more
TL;DR: This paper reviews the evolution of neuromorphic computing technique in both computing model and hardware implementation from a historical perspective and presents some emerging technologies that may potentially change the landscape of neuromorph computing in the future.