WD
William J. Dally
cs.CVcs.LGcs.ARcs.NEcs.DCstat.MLcs.AIcs.PFcs.CLcs.OS
On Valency
published · living versionsW_uwxtqkrf·v1 · currentpublished
Learning both Weights and Connections for Efficient Neural Networks
with Song Han, Jeff Pool, John Tran
1 version
Preprints & journals
25 papers in the corpus · 2015–2023SpArch: Efficient Architecture for Sparse Matrix Multiplication2002.08947v1 · Zhekai Zhang, Hanrui Wang, Song Han et al.2020 · 284 citationsarXiv
Retrospective: EIE: Efficient Inference Engine on Sparse and Compressed Neural Network2306.09552v1 · Song Han, Xingyu Liu, Huizi Mao et al.2023 · 1 citationarXiv
SatIn: Hardware for Boolean Satisfiability Inference2303.02588v1 · Chenzhuo Zhu, Alexander C. Rucker, Yawen Wang et al.2023 · 0 citationsarXiv
GPU-Initiated On-Demand High-Throughput Storage Access in the BaM System Architecture2203.04910v3 · Zaid Qureshi, Vikram Sharma Mailthody, Isaac Gelado et al.2022 · 48 citationsASPLOS 2023: Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2
Optimal Clipping and Magnitude-aware Differentiation for Improved Quantization-aware Training2206.06501v1 · Charbel Sakr, Steve Dai, Rangharajan Venkatesan et al.2022 · 11 citationsarXiv
Champagne: Automated Whole-Genome Phylogenomic Character Matrix Method Using Large Genomic Indels for Homoplasy-Free Inference.35171243 · Schull, James K, Turakhia, Yatish, Hemker, James A et al.2022 · 11 citationsGenome biology and evolution. 2022;14(3)
PatchNet -- Short-range Template Matching for Efficient Video Processing2103.07371v1 · Huizi Mao, Sibo Zhu, Song Han et al.2021 · 2 citationsarXiv
VS-Quant: Per-vector Scaled Quantization for Accurate Low-Precision Neural Network Inference2102.04503v1 · Steve Dai, Rangharajan Venkatesan, Haoxing Ren et al.2021 · 15 citationsarXiv
Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training1712.01887v3 · Yujun Lin, Song Han, Huizi Mao et al.2017 · 1,042 citationsICLR 2018
Champagne: Whole-genome phylogenomic character matrix method places Myomorpha basal in Rodentia10.1101/803957v1 · Schull, J. K., Turakhia, Y., Dally, W. J. et al.2019 · 8 citationsbioRxiv
CaTDet: Cascaded Tracked Detector for Efficient Object Detection from Video1810.00434v2 · Huizi Mao, Taeyoung Kong, William J. Dally2018 · 15 citationsarXiv
Efficient Sparse-Winograd Convolutional Neural Networks1802.06367v1 · Xingyu Liu, Jeff Pool, Song Han et al.2018 · 47 citationsarXiv
SCNN: An Accelerator for Compressed-sparse Convolutional Neural Networks1708.04485v1 · Angshuman Parashar, Minsoo Rhu, Anurag Mukkara et al.2017 · 122 citationsarXiv
Exploring the Regularity of Sparse Structure in Convolutional Neural Networks1705.08922v3 · Huizi Mao, Song Han, Jeff Pool et al.2017 · 229 citationsarXiv
Deep Generative Adversarial Networks for Compressed Sensing Automates MRI1706.00051v1 · Morteza Mardani, Enhao Gong, Joseph Y. Cheng et al.2017 · 131 citationsarXiv
Trained Ternary Quantization1612.01064v3 · Chenzhuo Zhu, Song Han, Huizi Mao et al.2016 · 846 citationsarXiv
DSD: Dense-Sparse-Dense Training for Deep Neural Networks1607.04381v2 · Song Han, Jeff Pool, Sharan Narang et al.2016 · 163 citationsarXiv
ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA1612.00694v2 · Song Han, Junlong Kang, Huizi Mao et al.2016 · 61 citationsarXiv
Darwin: A Hardware-acceleration Framework for Genomic Sequence Alignment10.1101/092171v2 · Turakhia, Y., Zheng, K. J., Bejerano, G. et al.2017 · 16 citationsbioRxiv
HoLiSwap: Reducing Wire Energy in L1 Caches1701.03878v1 · Yatish Turakhia, Subhasis Das, Tor M. Aamodt et al.2017 · 0 citationsarXiv
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size1602.07360v4 · Forrest N. Iandola, Song Han, Matthew W. Moskewicz et al.2016 · 6,589 citationsarXiv
CG-OoO: Energy-Efficient Coarse-Grain Out-of-Order Execution1606.01607v1 · Milad Mohammadi, Tor M. Aamodt, William J. Dally2016 · 0 citationsarXiv
EIE: Efficient Inference Engine on Compressed Deep Neural Network1602.01528v2 · Song Han, Xingyu Liu, Huizi Mao et al.2016 · 1,069 citationsarXiv
Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding1510.00149v5 · Song Han, Huizi Mao, William J. Dally2015 · 3,522 citationsarXiv
Learning both Weights and Connections for Efficient Neural Networks1506.02626v3 · Song Han, Jeff Pool, John Tran et al.2015 · 662 citationsarXivon Valency
Career total: 454 works. 25 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.