Daniel Soudry
Artificial Intelligence · 2014–2023
A researcher in the Science corpus: 29 papers; trusts 1,988 researchers and is trusted by 2,208 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 678 citations into it; #892 of 36,961 by trust here, #734 by citations
- Computer Vision and Pattern Recognition — 442 citations into it; #1,354 of 21,973 by trust here, #810 by citations
- Optimization & Training — 267 citations into it; #278 of 2,605 by trust here, #208 by citations
- Model Architectures — 134 citations into it; #1,281 of 2,288 by trust here, #1,438 by citations
- Efficiency & Compression — 121 citations into it; #99 of 1,273 by trust here, #52 by citations
- Computational Mechanics — 78 citations into it; #1,904 of 10,021 by trust here, #1,168 by citations
- Representation & Self-Supervised Learning — 71 citations into it
- Scaling & Learning Theory — 67 citations into it; #16 of 429 by trust here, #36 by citations
Whom Daniel Soudry trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Alex Krizhevsky
- Geoffrey E. Hinton
- Yann LeCun
- Kaiming He
- Yoshua Bengio
- Diederik P. Kingma
- L. Eon Bottou
- Alex Graves
- Ilya Sutskever
- Radford M. Neal
Who trusts Daniel Soudry overall
- Yuanzhi Li
- Elad Hoffer
- Tengyu Ma
- Simon Shaolei Du
- Colin Wei
- Sanjeev Arora
- Jason D. Lee
- Itay Hubara
- Yoshua Bengio
- Zeyuan Allen-Zhu
Papers from Daniel Soudry's perspective
Ordered by how strongly the researchers Daniel Soudry 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)
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- Attention is All you Need (Neural Information Processing Systems)
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Train longer, generalize better: closing the generalization gap in large batch training of neural networks (2017) — 889 citations
- Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations (2016) — 2,112 citations
- The Implicit Bias of Gradient Descent on Separable Data (2017) — 1,145 citations
- Binarized Neural Networks (2016) — 2,178 citations
- Binarized Neural Networks (2016) — 1,334 citations
- Augment Your Batch: Improving Generalization Through Instance Repetition (2020) — 256 citations
- Implicit Bias of Gradient Descent on Linear Convolutional Networks (2018) — 483 citations
- Expectation Backpropagation: Parameter-Free Training of Multilayer Neural Networks with Continuous or Discrete Weights (2014) — 236 citations
- No bad local minima: Data independent training error guarantees for multilayer neural networks (2016) — 244 citations
- Task Agnostic Continual Learning Using Online Variational Bayes (2018) — 130 citations
- Norm matters: efficient and accurate normalization schemes in deep networks (2018) — 191 citations
- Characterizing Implicit Bias in Terms of Optimization Geometry (2018) — 476 citations
- The Knowledge Within: Methods for Data-Free Model Compression (2019) — 117 citations
- Training Binary Multilayer Neural Networks for Image Classification using Expectation Backpropagation (2015) — 52 citations
- Exponentially vanishing sub-optimal local minima in multilayer neural networks (2017) — 105 citations
- Kernel and Rich Regimes in Overparametrized Models (2019) — 437 citations
- Scalable Methods for 8-bit Training of Neural Networks (2018) — 375 citations
- Kernel and Deep Regimes in Overparametrized Models (2019) — 33 citations
- Fix your classifier: the marginal value of training the last weight layer (2018) — 107 citations
- Task-Agnostic Continual Learning Using Online Variational Bayes With Fixed-Point Updates (2020) — 51 citations