Thomas Litfin

Molecular Biology · 2018–2020

A researcher in the Science corpus: 4 papers; trusts 38 researchers and is trusted by 3 researchers here, as inferred from the citation graph.

Subfields

• Molecular Biology — 124 citations into it; #9,886 of 17,773 by trust here, #9,727 by citations
• Materials Chemistry — 55 citations into it
• Computational Biology & Bioinformatics — 39 citations into it
• Model Architectures — 28 citations into it
• Artificial Intelligence — 26 citations into it
• Spectroscopy — 22 citations into it
• Optimization & Training — 19 citations into it
• Computer Vision and Pattern Recognition — 14 citations into it

Whom Thomas Litfin trusts overall

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

1. Yuhai Wu
2. Vladimir N Uversky
3. Jack Hanson
4. Kuldip K. Paliwal
5. Sepp Hochreiter
6. Diederik P. Kingma
7. Sergey Ioffe
8. Christian Szegedy
9. Geoffrey E. Hinton
10. Kaiming He

Who trusts Thomas Litfin overall

1. Jack Hanson
2. Kuldip K. Paliwal

Papers from Thomas Litfin's perspective

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

1. Long Short-Term Memory
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
3. ImageNet classification with deep convolutional neural networks
4. Gradient-based learning applied to document recognition
5. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
6. Attention is All you Need (Neural Information Processing Systems)
7. ImageNet: A large-scale hierarchical image database
8. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
9. Learning Multiple Layers of Features from Tiny Images
10. Going deeper with convolutions

Their papers

• Accurate prediction of protein contact maps by coupling residual two-dimensional bidirectional long short-term memory with convolutional neural networks (2018) — 158 citations
• Improving prediction of protein secondary structure, backbone angles, solvent accessibility and contact numbers by using predicted contact maps and an ensemble of recurrent and residual convolutional neural networks (2018) — 171 citations
• Critical assessment of protein intrinsic disorder prediction (2020) — 286 citations
• SPOT-Disorder2: Improved Protein Intrinsic Disorder Prediction by Ensembled Deep Learning (2019) — 139 citations