Samuel L. Smith
Artificial Intelligence · 2014–2023
A researcher in the Science corpus: 16 papers; trusts 1,992 researchers and is trusted by 1,241 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 502 citations into it; #1,315 of 36,961 by trust here, #2,820 by citations
- Computer Vision and Pattern Recognition — 302 citations into it; #1,897 of 21,973 by trust here, #2,925 by citations
- Optimization & Training — 276 citations into it; #371 of 2,605 by trust here, #347 by citations
- Model Architectures — 107 citations into it; #1,364 of 2,288 by trust here, #1,834 by citations
- Scaling & Learning Theory — 49 citations into it; #139 of 429 by trust here, #209 by citations
- Representation & Self-Supervised Learning — 45 citations into it; #1,128 of 3,156 by trust here, #1,395 by citations
- Statistical and Nonlinear Physics — 36 citations into it
- Statistics and Probability — 36 citations into it; #4,861 of 13,188 by trust here, #5,477 by citations
Whom Samuel L. Smith trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Kaiming He
- Alex Krizhevsky
- Geoffrey E. Hinton
- Diederik P. Kingma
- Yoshua Bengio
- Ilya Sutskever
- Yann LeCun
- Christian Szegedy
- Ross B. Girshick
- Sergey Ioffe
Who trusts Samuel L. Smith overall
- Soham De
- Andrew Brock
- Mikel Artetxe
- Dominic Masters
- Ivan Vulic
- Sebastian Ruder
- Quoc V. Le
- Wujie Wen
- Anne Lauscher
- Stanislav Fort
Papers from Samuel L. Smith's perspective
Ordered by how strongly the researchers Samuel L. Smith trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- High-Performance Large-Scale Image Recognition Without Normalization (2021) — 638 citations
- Don't Decay the Learning Rate, Increase the Batch Size (2017) — 1,135 citations
- A Bayesian Perspective on Generalization and Stochastic Gradient Descent (2017) — 309 citations
- Offline bilingual word vectors, orthogonal transformations and the inverted softmax (2017) — 559 citations
- Batch Normalization Biases Residual Blocks Towards the Identity Function in Deep Networks (2020) — 166 citations
- Characterizing signal propagation to close the performance gap in unnormalized ResNets (2021) — 145 citations
- BYOL works even without batch statistics (2020) — 131 citations
- The Effect of Network Width on Stochastic Gradient Descent and Generalization: an Empirical Study (2019) — 61 citations
- Unlocking High-Accuracy Differentially Private Image Classification through Scale (2022) — 286 citations
- Batch Normalization has Multiple Benefits: An Empirical Study on Residual Networks (2019) — 6 citations
- On the Generalization Benefit of Noise in Stochastic Gradient Descent (2020) — 129 citations
- Batch Normalization Biases Deep Residual Networks Towards Shallow Paths (2020) — 20 citations
- Stochastic natural gradient descent draws posterior samples in function space (2018) — 8 citations
- Stochastic Gradient Descent (2014) — 607 citations
- Resurrecting Recurrent Neural Networks for Long Sequences (2023) — 516 citations
- Drawing Multiple Augmentation Samples Per Image During Training Efficiently Decreases Test Error (2021) — 36 citations