Leslie N. Smith

Artificial Intelligence · 2015–2018

A researcher in the Science corpus: 8 papers; trusts 827 researchers and is trusted by 236 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 119 citations into it; #1,051 of 35,345 by trust here, #4,420 by citations
• Optimization & Training — 98 citations into it; #115 of 2,601 by trust here, #455 by citations
• Computer Vision and Pattern Recognition — 78 citations into it; #2,909 of 21,575 by trust here, #5,375 by citations
• Model Architectures — 37 citations into it
• Scaling & Learning Theory — 19 citations into it
• Management Science and Operations Research — 15 citations into it
• Natural Language Processing — 9 citations into it
• Computational Mechanics — 8 citations into it

Whom Leslie N. Smith trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Yoshua Bengio
2. Matthew D. Zeiler
3. Alex Krizhevsky
4. Geoffrey E. Hinton
5. Kaiming He
6. Diederik P. Kingma
7. Ilya Sutskever
8. Yann LeCun
9. Christian Szegedy
10. James Martens

Who trusts Leslie N. Smith overall

1. Jeremy Howard
2. Diganta Misra
3. Carl Sabottke
4. Rakesh Chada
5. Artem Abzaliev
6. Chunyuan Li
7. Nicholay Topin
8. Georgios Kapidis
9. Tuyen T. T. Truong
10. Jenthe Thienpondt

Papers from Leslie N. Smith's perspective

Ordered by how strongly the researchers Leslie N. Smith trusts endorse each paper. Same corpus, a different order for every researcher.

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Long Short-Term Memory
5. Attention is All you Need (Neural Information Processing Systems)
6. Gradient-based learning applied to document recognition
7. ImageNet: A large-scale hierarchical image database
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. ImageNet Large Scale Visual Recognition Challenge
10. Learning Multiple Layers of Features from Tiny Images

Their papers

• Cyclical Learning Rates for Training Neural Networks (2015) — 2,966 citations
• Super-Convergence: Very Fast Training of Residual Networks Using Large Learning Rates (2017) — 524 citations
• Gradual DropIn of Layers to Train Very Deep Neural Networks (2015) — 37 citations
• A disciplined approach to neural network hyper-parameters: Part 1 - learning rate, batch size, momentum, and weight decay (2018) — 1,200 citations
• Super-convergence: very fast training of neural networks using large learning rates (2018) — 1,797 citations
• Exploring loss function topology with cyclical learning rates (2017) — 27 citations
• Selecting Subgoals using Deep Learning in Minecraft : A Preliminary Report (2016)
• No More Pesky Learning Rate Guessing Games (2015) — 163 citations