Jeffrey Pennington
Artificial Intelligence · 2011–2024
A researcher in the Science corpus: 25 papers; trusts 856 researchers and is trusted by 9,893 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 469 citations into it; #105 of 36,961 by trust here, #191 by citations
- Computer Vision and Pattern Recognition — 157 citations into it; #5,802 of 21,973 by trust here, #6,327 by citations
- Optimization & Training — 142 citations into it; #581 of 2,605 by trust here, #529 by citations
- Scaling & Learning Theory — 122 citations into it; #48 of 429 by trust here, #53 by citations
- Model Architectures — 116 citations into it; #528 of 2,288 by trust here, #578 by citations
- Statistical and Nonlinear Physics — 79 citations into it; #992 of 10,175 by trust here, #624 by citations
- Natural Language Processing — 71 citations into it; #20 of 5,725 by trust here, #52 by citations
- Nuclear and High Energy Physics — 54 citations into it; #2,261 of 6,167 by trust here, #4,169 by citations
Whom Jeffrey Pennington trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Yoshua Bengio
- Geoffrey E. Hinton
- Diederik P. Kingma
- Tomas Mikolov
- Alex Krizhevsky
- Yann LeCun
- Ilya Sutskever
- Kaiming He
- Ronan Collobert
- Jimmy Ba
Who trusts Jeffrey Pennington overall
- Greg Yang
- Percy Liang
- Richard Socher
- Mohit Bansal
- Yoav Goldberg
- Yoshua Bengio
- Zhe Gan
- Yi Tay
- Christopher D. Manning
- Caiming Xiong
Papers from Jeffrey Pennington's perspective
Ordered by how strongly the researchers Jeffrey Pennington 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
- Learning Multiple Layers of Features from Tiny Images
- 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)
Their papers
- GloVe: Global Vectors for Word Representation (2014) — 34,790 citations
- Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions (2011) — 1,357 citations
- Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection (2011) — 971 citations
- Wide neural networks of any depth evolve as linear models under gradient descent (2019) — 1,337 citations
- Deep Neural Networks as Gaussian Processes (2017) — 1,255 citations
- Sensitivity and Generalization in Neural Networks: an Empirical Study (2018) — 514 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
- Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice (2017) — 307 citations
- Geometry of Neural Network Loss Surfaces via Random Matrix Theory (2017) — 169 citations
- The Emergence of Spectral Universality in Deep Networks (2018) — 185 citations
- Dynamical Isometry and a Mean Field Theory of RNNs: Gating Enables Signal Propagation in Recurrent Neural Networks (2018) — 126 citations
- Dynamical Isometry and a Mean Field Theory of LSTMs and GRUs (2019) — 44 citations
- Spherical Random Features for Polynomial Kernels (2015) — 78 citations
- Disentangling trainability and generalization in deep learning (2019) — 35 citations
- Statistical mechanics of deep learning (2024) — 234 citations
- The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks (2020) — 74 citations
- Estimating the Spectral Density of Large Implicit Matrices (2018) — 40 citations
- ournal of Statistical Mechanics : J Theory and Experiment (2019)
- Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models (2023) — 337 citations