Sungjin Ahn
Artificial Intelligence · 2012–2020
A researcher in the Science corpus: 13 papers; trusts 1,441 researchers and is trusted by 869 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 305 citations into it; #1,149 of 36,961 by trust here, #2,352 by citations
- Computer Vision and Pattern Recognition — 197 citations into it; #7,887 of 21,973 by trust here, #5,262 by citations
- Natural Language Processing — 86 citations into it; #1,040 of 5,725 by trust here, #932 by citations
- Generative Models — 65 citations into it; #1,062 of 1,963 by trust here, #1,420 by citations
- Representation & Self-Supervised Learning — 62 citations into it
- Model Architectures — 56 citations into it; #515 of 2,288 by trust here, #639 by citations
- Probabilistic & Bayesian Methods — 40 citations into it; #596 of 1,526 by trust here, #305 by citations
- Optimization & Training — 38 citations into it; #1,022 of 2,605 by trust here, #1,107 by citations
Whom Sungjin Ahn trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yoshua Bengio
- Geoffrey E. Hinton
- Diederik P. Kingma
- Alex Graves
- Ilya Sutskever
- Alex Krizhevsky
- Ronald J. Williams
- Oriol Vinyals
- Yann LeCun
- J. Urgen Schmidhuber
Who trusts Sungjin Ahn overall
- Yoshua Bengio
- Chunyuan Li
- Caiming Xiong
- Ruslan Salakhutdinov
- Li Dong
- Felix Stahlberg
- Richard Socher
- Mirella Lapata
- Ratish Puduppully
- Danilo Jimenez Rezende
Papers from Sungjin Ahn's perspective
Ordered by how strongly the researchers Sungjin Ahn 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
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- Learning Multiple Layers of Features from Tiny Images
Their papers
- Pointing the Unknown Words (2016) — 537 citations
- Hierarchical Multiscale Recurrent Neural Networks (2016) — 568 citations
- A Neural Knowledge Language Model (2016) — 124 citations
- Bayesian Model-Agnostic Meta-Learning (2018) — 548 citations
- Bayesian Posterior Sampling via Stochastic Gradient Fisher Scoring (2012) — 318 citations
- Hierarchical Memory Networks (2016) — 88 citations
- Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus (2016) — 300 citations
- SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition (2020) — 280 citations
- SCALOR: Generative World Models with Scalable Object Representations (2019) — 154 citations
- Scalable Object-Oriented Sequential Generative Models (2019) — 16 citations
- ROOTS: Object-Centric Representation and Rendering of 3D Scenes (2020) — 57 citations
- Denoising Criterion for Variational Auto-Encoding Framework (2015) — 224 citations
- Generative Neurosymbolic Machines (2020) — 73 citations