Jascha Narain Sohl-Dickstein
Artificial Intelligence · 2003–2024
A researcher in the Science corpus: 55 papers; trusts 2,489 researchers and is trusted by 9,233 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 1,124 citations into it; #202 of 36,961 by trust here, #255 by citations
- Computer Vision and Pattern Recognition — 573 citations into it; #488 of 21,973 by trust here, #466 by citations
- Optimization & Training — 333 citations into it; #455 of 2,605 by trust here, #301 by citations
- Probabilistic & Bayesian Methods — 274 citations into it; #41 of 1,526 by trust here, #19 by citations
- Generative Models — 187 citations into it; #29 of 1,963 by trust here, #39 by citations
- Model Architectures — 186 citations into it; #309 of 2,288 by trust here, #312 by citations
- Statistics and Probability — 159 citations into it; #3,578 of 13,188 by trust here, #3,836 by citations
- Scaling & Learning Theory — 122 citations into it; #62 of 429 by trust here, #33 by citations
Whom Jascha Narain Sohl-Dickstein trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Radford M. Neal
- Alex Krizhevsky
- Yoshua Bengio
- Diederik P. Kingma
- Yann LeCun
- Kaiming He
- Ilya Sutskever
- L. Eon Bottou
- Ruslan Salakhutdinov
Who trusts Jascha Narain Sohl-Dickstein overall
- Yang Song
- Diederik P. Kingma
- Jonathan Ho
- Yoshua Bengio
- Arash Vahdat
- Stefano Ermon
- Sergey Levine
- Jiaming Song
- Greg Yang
- Ruslan Salakhutdinov
Papers from Jascha Narain Sohl-Dickstein's perspective
Ordered by how strongly the researchers Jascha Narain Sohl-Dickstein 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)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- 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)
- Learning Multiple Layers of Features from Tiny Images
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
Their papers
- Density estimation using Real NVP (2016) — 4,503 citations
- Deep Unsupervised Learning using Nonequilibrium Thermodynamics (2015) — 10,395 citations
- Unrolled Generative Adversarial Networks (2016) — 1,076 citations
- Score-Based Generative Modeling through Stochastic Differential Equations (2020) — 11,485 citations
- Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models (2022) — 2,561 citations
- Wide neural networks of any depth evolve as linear models under gradient descent (2019) — 1,337 citations
- Learned Optimizers that Scale and Generalize (2017) — 308 citations
- On the Expressive Power of Deep Neural Networks (2016) — 897 citations
- Deep Neural Networks as Gaussian Processes (2017) — 1,255 citations
- REBAR: Low-variance, unbiased gradient estimates for discrete latent variable models (2017) — 303 citations
- Exponential expressivity in deep neural networks through transient chaos (2016) — 683 citations
- Sensitivity and Generalization in Neural Networks: an Empirical Study (2018) — 514 citations
- Capacity and Trainability in Recurrent Neural Networks (2016) — 215 citations
- Measuring the Effects of Data Parallelism on Neural Network Training (2018) — 484 citations
- Meta-Learning Update Rules for Unsupervised Representation Learning (2018) — 132 citations
- Fast large-scale optimization by unifying stochastic gradient and quasi-Newton methods (2013) — 130 citations
- Deep Information Propagation (2016) — 429 citations
- Bayesian Deep Convolutional Networks with Many Channels are Gaussian Processes (2018) — 331 citations
- Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10, 000-Layer Vanilla Convolutional Neural Networks (2018) — 392 citations
- Language Model Cascades (2022) — 119 citations