Dmitry Kobak
Molecular Biology · with Berens · 2014–2024
A researcher in the Science corpus: 8 papers; trusts 62 researchers and is trusted by 18 researchers here, as inferred from the citation graph.
Subfields
- Molecular Biology — 68 citations into it; #5,560 of 17,773 by trust here, #12,227 by citations
- Representation & Self-Supervised Learning — 54 citations into it; #1,256 of 3,145 by trust here, #2,178 by citations
- Computer Vision and Pattern Recognition — 39 citations into it
- Biophysics — 35 citations into it
- Artificial Intelligence — 27 citations into it
- Computational Biology & Bioinformatics — 10 citations into it; #296 of 660 by trust here, #590 by citations
- Computational Mechanics — 7 citations into it
- Computational Theory and Mathematics — 7 citations into it
Whom Dmitry Kobak trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- L. V. D. van der Maaten
- Geoffrey E. Hinton
- Leland McInnes
- George C. Linderman
- Mikhail Belkin
- Etienne Becht
- Sam T. Roweis
- John Healy
- Benjamin M. Schmidt
- Sanjeev Arora
Who trusts Dmitry Kobak overall
- J. Böhm
- George C. Linderman
- Philipp Berens
- Chengxi Zang
- Cynthia Rudin
- Yingfan Wang
- Tim Sainburg
- Pavlin Gregor Policar
- Anna C. Belkina
- Leland McInnes
Papers from Dmitry Kobak's perspective
Ordered by how strongly the researchers Dmitry Kobak 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
- Gradient-based learning applied to document recognition
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- Learning Multiple Layers of Features from Tiny Images
- ImageNet: A large-scale hierarchical image database
- ImageNet Large Scale Visual Recognition Challenge
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
Their papers
- The art of using t-SNE for single-cell transcriptomics (2018) — 1,041 citations
- Heavy-tailed kernels reveal a finer cluster structure in t-SNE visualisations (2019) — 46 citations
- UMAP does not preserve global structure any better than t-SNE when using the same initialization (2019) — 46 citations
- Initialization is critical for preserving global data structure in both t-SNE and UMAP (2021) — 318 citations
- The landscape of biomedical research (2024)
- Correction to: Heavy-Tailed Kernels Reveal a Finer Cluster Structure in t-SNE Visualisations (2020)
- A Unifying Perspective on Neighbor Embeddings along the Attraction-Repulsion Spectrum (2020) — 26 citations
- Demixed principal component analysis of neural population data (2014) — 567 citations