Search

Your search keyword '"Cheng Zhong"' showing total 6,529 results
Start Over Author "Cheng Zhong"

Refine your results

more »

more »

more »

more »

more »

more »
6,529 results on '"Cheng Zhong"'

273. Focused Quantization for Sparse CNNs

Author

Zhao, Yiren, Gao, Xitong, Bates, Daniel, Mullins, Robert, and Xu, Cheng-Zhong

Subjects
Computer Science - Machine Learning, Statistics - Machine Learning
Abstract

Deep convolutional neural networks (CNNs) are powerful tools for a wide range of vision tasks, but the enormous amount of memory and compute resources required by CNNs pose a challenge in deploying them on constrained devices. Existing compression techniques, while excelling at reducing model sizes, struggle to be computationally friendly. In this paper, we attend to the statistical properties of sparse CNNs and present focused quantization, a novel quantization strategy based on power-of-two values, which exploits the weight distributions after fine-grained pruning. The proposed method dynamically discovers the most effective numerical representation for weights in layers with varying sparsities, significantly reducing model sizes. Multiplications in quantized CNNs are replaced with much cheaper bit-shift operations for efficient inference. Coupled with lossless encoding, we built a compression pipeline that provides CNNs with high compression ratios (CR), low computation cost and minimal loss in accuracy. In ResNet-50, we achieved a 18.08x CR with only 0.24% loss in top-5 accuracy, outperforming existing compression methods. We fully compressed a ResNet-18 and found that it is not only higher in CR and top-5 accuracy, but also more hardware efficient as it requires fewer logic gates to implement when compared to other state-of-the-art quantization methods assuming the same throughput., Comment: To appear in NeurIPS 2019, this is the same paper adapted for viewing on arXiv. TL;DR: Better size/accuracy trade-off of compressed sparse models with focused quantization. 11 pages, 5 figures, 4 tables

Published
2019

274. Sitatapatra: Blocking the Transfer of Adversarial Samples

Author

Shumailov, Ilia, Gao, Xitong, Zhao, Yiren, Mullins, Robert, Anderson, Ross, and Xu, Cheng-Zhong

Subjects
Computer Science - Machine Learning, Computer Science - Cryptography and Security, Statistics - Machine Learning
Abstract

Convolutional Neural Networks (CNNs) are widely used to solve classification tasks in computer vision. However, they can be tricked into misclassifying specially crafted `adversarial' samples -- and samples built to trick one model often work alarmingly well against other models trained on the same task. In this paper we introduce Sitatapatra, a system designed to block the transfer of adversarial samples. It diversifies neural networks using a key, as in cryptography, and provides a mechanism for detecting attacks. What's more, when adversarial samples are detected they can typically be traced back to the individual device that was used to develop them. The run-time overheads are minimal permitting the use of Sitatapatra on constrained systems.

Published
2019

275. Comprehensive analysis of chromothripsis in 2,658 human cancers using whole-genome sequencing

Author

Cortés-Ciriano, Isidro, Lee, Jake June-Koo, Xi, Ruibin, Jain, Dhawal, Jung, Youngsook L, Yang, Lixing, Gordenin, Dmitry, Klimczak, Leszek J, Zhang, Cheng-Zhong, Pellman, David S, and Park, Peter J

Subjects
Cancer, Genetics, Human Genome, Aetiology, 2.1 Biological and endogenous factors, Good Health and Well Being, Chromothripsis, Evolution, Molecular, Genome, Human, Genomics, Humans, Mutation, Neoplasms, Whole Genome Sequencing, PCAWG Structural Variation Working Group, PCAWG Consortium, Biological Sciences, Medical and Health Sciences, Developmental Biology
Abstract

Chromothripsis is a mutational phenomenon characterized by massive, clustered genomic rearrangements that occurs in cancer and other diseases. Recent studies in selected cancer types have suggested that chromothripsis may be more common than initially inferred from low-resolution copy-number data. Here, as part of the Pan-Cancer Analysis of Whole Genomes (PCAWG) Consortium of the International Cancer Genome Consortium (ICGC) and The Cancer Genome Atlas (TCGA), we analyze patterns of chromothripsis across 2,658 tumors from 38 cancer types using whole-genome sequencing data. We find that chromothripsis events are pervasive across cancers, with a frequency of more than 50% in several cancer types. Whereas canonical chromothripsis profiles display oscillations between two copy-number states, a considerable fraction of events involve multiple chromosomes and additional structural alterations. In addition to non-homologous end joining, we detect signatures of replication-associated processes and templated insertions. Chromothripsis contributes to oncogene amplification and to inactivation of genes such as mismatch-repair-related genes. These findings show that chromothripsis is a major process that drives genome evolution in human cancer.

Published
2020

276. Analyses of non-coding somatic drivers in 2,658 cancer whole genomes.

Author

Rheinbay, Esther, Nielsen, Morten Muhlig, Abascal, Federico, Wala, Jeremiah A, Shapira, Ofer, Tiao, Grace, Hornshøj, Henrik, Hess, Julian M, Juul, Randi Istrup, Lin, Ziao, Feuerbach, Lars, Sabarinathan, Radhakrishnan, Madsen, Tobias, Kim, Jaegil, Mularoni, Loris, Shuai, Shimin, Lanzós, Andrés, Herrmann, Carl, Maruvka, Yosef E, Shen, Ciyue, Amin, Samirkumar B, Bandopadhayay, Pratiti, Bertl, Johanna, Boroevich, Keith A, Busanovich, John, Carlevaro-Fita, Joana, Chakravarty, Dimple, Chan, Calvin Wing Yiu, Craft, David, Dhingra, Priyanka, Diamanti, Klev, Fonseca, Nuno A, Gonzalez-Perez, Abel, Guo, Qianyun, Hamilton, Mark P, Haradhvala, Nicholas J, Hong, Chen, Isaev, Keren, Johnson, Todd A, Juul, Malene, Kahles, Andre, Kahraman, Abdullah, Kim, Youngwook, Komorowski, Jan, Kumar, Kiran, Kumar, Sushant, Lee, Donghoon, Lehmann, Kjong-Van, Li, Yilong, Liu, Eric Minwei, Lochovsky, Lucas, Park, Keunchil, Pich, Oriol, Roberts, Nicola D, Saksena, Gordon, Schumacher, Steven E, Sidiropoulos, Nikos, Sieverling, Lina, Sinnott-Armstrong, Nasa, Stewart, Chip, Tamborero, David, Tubio, Jose MC, Umer, Husen M, Uusküla-Reimand, Liis, Wadelius, Claes, Wadi, Lina, Yao, Xiaotong, Zhang, Cheng-Zhong, Zhang, Jing, Haber, James E, Hobolth, Asger, Imielinski, Marcin, Kellis, Manolis, Lawrence, Michael S, von Mering, Christian, Nakagawa, Hidewaki, Raphael, Benjamin J, Rubin, Mark A, Sander, Chris, Stein, Lincoln D, Stuart, Joshua M, Tsunoda, Tatsuhiko, Wheeler, David A, Johnson, Rory, Reimand, Jüri, Gerstein, Mark, Khurana, Ekta, Campbell, Peter J, López-Bigas, Núria, PCAWG Drivers and Functional Interpretation Working Group, PCAWG Structural Variation Working Group, Weischenfeldt, Joachim, Beroukhim, Rameen, Martincorena, Iñigo, Pedersen, Jakob Skou, Getz, Gad, and PCAWG Consortium

Subjects
PCAWG Drivers and Functional Interpretation Working Group, PCAWG Structural Variation Working Group, PCAWG Consortium, Humans, Neoplasms, Gene Expression Regulation, Neoplastic, Mutation, Genome, Human, Databases, Genetic, DNA Breaks, INDEL Mutation, Genome-Wide Association Study, Gene Expression Regulation, Neoplastic, Genome, Human, Databases, Genetic, General Science & Technology
Abstract

The discovery of drivers of cancer has traditionally focused on protein-coding genes1-4. Here we present analyses of driver point mutations and structural variants in non-coding regions across 2,658 genomes from the Pan-Cancer Analysis of Whole Genomes (PCAWG) Consortium5 of the International Cancer Genome Consortium (ICGC) and The Cancer Genome Atlas (TCGA). For point mutations, we developed a statistically rigorous strategy for combining significance levels from multiple methods of driver discovery that overcomes the limitations of individual methods. For structural variants, we present two methods of driver discovery, and identify regions that are significantly affected by recurrent breakpoints and recurrent somatic juxtapositions. Our analyses confirm previously reported drivers6,7, raise doubts about others and identify novel candidates, including point mutations in the 5' region of TP53, in the 3' untranslated regions of NFKBIZ and TOB1, focal deletions in BRD4 and rearrangements in the loci of AKR1C genes. We show that although point mutations and structural variants that drive cancer are less frequent in non-coding genes and regulatory sequences than in protein-coding genes, additional examples of these drivers will be found as more cancer genomes become available.

Published
2020

277. Dynamic Channel Pruning: Feature Boosting and Suppression

Author

Gao, Xitong, Zhao, Yiren, Dudziak, Łukasz, Mullins, Robert, and Xu, Cheng-zhong

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Making deep convolutional neural networks more accurate typically comes at the cost of increased computational and memory resources. In this paper, we reduce this cost by exploiting the fact that the importance of features computed by convolutional layers is highly input-dependent, and propose feature boosting and suppression (FBS), a new method to predictively amplify salient convolutional channels and skip unimportant ones at run-time. FBS introduces small auxiliary connections to existing convolutional layers. In contrast to channel pruning methods which permanently remove channels, it preserves the full network structures and accelerates convolution by dynamically skipping unimportant input and output channels. FBS-augmented networks are trained with conventional stochastic gradient descent, making it readily available for many state-of-the-art CNNs. We compare FBS to a range of existing channel pruning and dynamic execution schemes and demonstrate large improvements on ImageNet classification. Experiments show that FBS can respectively provide $5\times$ and $2\times$ savings in compute on VGG-16 and ResNet-18, both with less than $0.6\%$ top-5 accuracy loss., Comment: 14 pages, 5 figures, 4 tables, published as a conference paper at ICLR 2019

Published
2018

294. An Experimental Analysis of Function Performance with Resource Allocation on Serverless Platform

Author

Zhang, Yonghe, Ye, Kejiang, Xu, Cheng-Zhong, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Ye, Kejiang, editor, and Zhang, Liang-Jie, editor

Published
2022
Full Text
View/download PDF

295. Performance Evaluation of Various RISC Processor Systems: A Case Study on ARM, MIPS and RISC-V

Author

Liu, Yu, Ye, Kejiang, Xu, Cheng-Zhong, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Ye, Kejiang, editor, and Zhang, Liang-Jie, editor

Published
2022
Full Text
View/download PDF

300. Diagnostic accuracy of magnetically guided capsule endoscopy with a detachable string for detecting oesophagogastric varices in adults with cirrhosis: prospective multicentre study

Author

Jiang, Xi, primary, Pan, Jun, additional, Xu, Qing, additional, Song, Yu-Hu, additional, Sun, Huan-Huan, additional, Peng, Cheng, additional, Qi, Xiao-Long, additional, Qian, Yang-Yang, additional, Zou, Wen-Bin, additional, Yang, Yang, additional, Jin, Shao-Qin, additional, Duan, Ben-Song, additional, Wu, Shan, additional, Chu, Ye, additional, Xiao, Ding-Hua, additional, Hu, Li-Juan, additional, Cao, Jun-Zhi, additional, Dai, Jin-Feng, additional, Liu, Xiao, additional, Xia, Tian, additional, Zhou, Wei, additional, Chen, Tao, additional, Zhou, Chun-Hua, additional, Wu, Wei, additional, Liu, Shao-Jun, additional, Yang, Zhen-Yu, additional, Wang, Fen, additional, Zhang, Lu, additional, Li, Cheng-Zhong, additional, Xu, Hao, additional, Wang, Jun-Xue, additional, Wei, Bo, additional, Lin, Yong, additional, Deng, Xing, additional, Qu, Li-Hong, additional, Shen, Ying-Qiu, additional, Wang, Hui, additional, Huang, Yi-Fei, additional, Bao, Hai-Biao, additional, Zhang, Shuo, additional, Li, Li, additional, Shi, Yi-Hai, additional, Wang, Xiao-Yan, additional, Zou, Duo-Wu, additional, Wan, Xin-Jian, additional, Xu, Mei-Dong, additional, Mao, Hua, additional, He, Chao-Hui, additional, Li, Zhen, additional, Zuo, Xiu-Li, additional, He, Shui-Xiang, additional, Xie, Xiao-Ping, additional, Liu, Jun, additional, Yang, Chang-Qing, additional, Spada, Cristiano, additional, Li, Zhao-Shen, additional, and Liao, Zhuan, additional

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results