Sergei Manzhos

Materials Chemistry · 2006–2018

A researcher in the Science corpus: 7 papers; trusts 10 researchers and is trusted by 16 researchers here, as inferred from the citation graph.

Subfields

• Materials Chemistry — 33 citations into it; #1,735 of 11,513 by trust here, #4,806 by citations
• Atomic and Molecular Physics, and Optics — 29 citations into it; #911 of 7,135 by trust here, #1,373 by citations
• Physical and Theoretical Chemistry — 12 citations into it
• Molecular Biology — 8 citations into it; #7,240 of 17,773 by trust here, #10,193 by citations
• Statistical and Nonlinear Physics — 8 citations into it
• Scaling & Learning Theory — 7 citations into it
• Model Architectures — 6 citations into it
• Nuclear and High Energy Physics — 5 citations into it

Whom Sergei Manzhos trusts overall

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

1. Kurt Hornik
2. Genyuan Li
3. Tucker Carrington Jr.
4. J. Behler
5. Ken-ichi Funahashi
6. Bernard Widrow
7. Martin H. Anthony
8. Bobby G. Sumpter
9. Andrew R. Barron
10. Vera Kurková

Who trusts Sergei Manzhos overall

1. B. A. Le
2. J. Behler
3. Julien Yvonnet
4. Pavlo O. Dral
5. Qi-Chang He
6. Kristof T. Schütt
7. Tucker Carrington Jr.
8. Oliver T. Unke
9. Kun Yao
10. Tobias Morawietz

Papers from Sergei Manzhos's perspective

Ordered by how strongly the researchers Sergei Manzhos 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. Gradient-based learning applied to document recognition
4. Learning Multiple Layers of Features from Tiny Images
5. Attention is All you Need (Neural Information Processing Systems)
6. Long Short-Term Memory
7. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
8. Going deeper with convolutions
9. ImageNet Large Scale Visual Recognition Challenge
10. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)

Their papers

• A random-sampling high dimensional model representation neural network for building potential energy surfaces. (2006) — 254 citations
• Neural network‐based approaches for building high dimensional and quantum dynamics‐friendly potential energy surfaces (2015) — 210 citations
• A nested molecule-independent neural network approach for high-quality potential fits. (2006) — 176 citations
• Using neural networks to represent potential surfaces as sums of products. (2006) — 162 citations
• Using redundant coordinates to represent potential energy surfaces with lower-dimensional functions. (2007) — 97 citations
• Molecular Engineering Using an Anthanthrone Dye for Low‐Cost Hole Transport Materials: A Strategy for Dopant‐Free, High‐Efficiency, and Stable Perovskite Solar Cells (2018) — 147 citations
• Using neural networks, optimized coordinates, and high-dimensional model representations to obtain a vinyl bromide potential surface. (2008) — 105 citations