William (Bill) J. Dally
Computer Vision and Pattern Recognition · 2000–2019
A researcher in the Science corpus: 33 papers; trusts 1,192 researchers and is trusted by 5,208 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 261 citations into it; #656 of 21,973 by trust here, #253 by citations
- Artificial Intelligence — 243 citations into it; #579 of 36,961 by trust here, #316 by citations
- Efficiency & Compression — 88 citations into it; #6 of 1,273 by trust here, #5 by citations
- Model Architectures — 85 citations into it
- Hardware and Architecture — 58 citations into it; #153 of 1,731 by trust here, #131 by citations
- Optimization & Training — 56 citations into it; #1,343 of 2,605 by trust here, #582 by citations
- Electrical and Electronic Engineering — 55 citations into it; #1,529 of 16,595 by trust here, #1,836 by citations
- Computer Networks and Communications — 41 citations into it; #743 of 9,996 by trust here, #642 by citations
Whom William (Bill) J. Dally trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Kaiming He
- Geoffrey E. Hinton
- Yann LeCun
- Karen Simonyan
- Yoshua Bengio
- Ilya Sutskever
- Christian Szegedy
- Ross B. Girshick
- Andrew Zisserman
Who trusts William (Bill) J. Dally overall
- Jingcao Hu
- Song Han
- Radu Marculescu
- Ji Lin
- Ümit Y. Ogras
- Yunhe Wang
- Han Cai
- Jonathan Frankle
- Yang He
- John Kim
Papers from William (Bill) J. Dally's perspective
Ordered by how strongly the researchers William (Bill) J. Dally trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Attention is All you Need (Neural Information Processing Systems)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Going deeper with convolutions
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Deep Compression: Compressing Deep Neural Network with Pruning, Trained Quantization and Huffman Coding (2015) — 10,226 citations
- Learning both Weights and Connections for Efficient Neural Network (2015) — 7,826 citations
- SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size (2016) — 8,474 citations
- Trained Ternary Quantization (2016) — 1,089 citations
- EIE: Efficient Inference Engine on Compressed Deep Neural Network (2016) — 2,611 citations
- DSD: Regularizing Deep Neural Networks with Dense-Sparse-Dense Training Flow (2016) — 83 citations
- Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training (2017) — 1,676 citations
- - LEVEL ACCURACY WITH 50 X FEWER PARAMETERS AND < 0 . 5 MB MODEL SIZE (2016)
- SCNN: An accelerator for compressed-sparse convolutional neural networks (2017) — 1,254 citations
- Exploring the Regularity of Sparse Structure in Convolutional Neural Networks (2017) — 258 citations
- Deep Generative Adversarial Networks for Compressed Sensing Automates MRI (2017) — 164 citations
- ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA (2016) — 659 citations
- Smart Memories: a modular reconfigurable architecture (2000) — 496 citations
- A delay model and speculative architecture for pipelined routers (2001) — 578 citations
- Simba: Scaling Deep-Learning Inference with Multi-Chip-Module-Based Architecture (2019) — 495 citations
- Register organization for media processing (2000) — 307 citations
- Imagine: Media Processing with Streams (2001) — 384 citations
- Flattened butterfly: a cost-efficient topology for high-radix networks (2007) — 489 citations
- Technology-Driven, Highly-Scalable Dragonfly Topology (2008) — 850 citations
- DSD: Dense-Sparse-Dense Training for Deep Neural Networks (2016) — 219 citations