Amar Shah

Artificial Intelligence · with Ghahramani · 2014–2015

A researcher in the Science corpus: 3 papers; trusts 40 researchers and is trusted by 66 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 20 citations into it; #3,776 of 35,345 by trust here, #6,848 by citations
• Optimization & Training — 13 citations into it
• Model Architectures — 10 citations into it; #459 of 2,278 by trust here, #776 by citations
• Probabilistic & Bayesian Methods — 9 citations into it
• Computational Theory and Mathematics — 6 citations into it; #2,133 of 12,182 by trust here, #4,850 by citations
• Management Science and Operations Research — 6 citations into it; #1,960 of 11,946 by trust here, #4,921 by citations

Whom Amar Shah trusts overall

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

1. Radford M. Neal
2. Jasper Snoek
3. David John Cameron MacKay
4. Andrew Gordon Wilson
5. Yoshua Bengio
6. Geoffrey E. Hinton
7. Ryan P. Adams
8. Donald R. Jones
9. Hugo Larochelle
10. Yann LeCun

Who trusts Amar Shah overall

1. Kirthevasan Kandasamy
2. Jian Wu
3. Michael U Gutmann
4. Eduardo C. Garrido-Merchán
5. Albert Gu
6. Shaojie Bai
7. Xilu Wang
8. Akshay Krishnamurthy
9. Guodong Zhang
10. Mikael Henaff

Papers from Amar Shah's perspective

Ordered by how strongly the researchers Amar Shah 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. Gradient-based learning applied to document recognition
6. Attention is All you Need (Neural Information Processing Systems)
7. ImageNet: A large-scale hierarchical image database
8. Learning Multiple Layers of Features from Tiny Images
9. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
10. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• Unitary Evolution Recurrent Neural Networks (2015) — 909 citations
• Parallel Predictive Entropy Search for Batch Global Optimization of Expensive Objective Functions (2015) — 169 citations
• Student-t Processes as Alternatives to Gaussian Processes (2014) — 227 citations