Jeffrey Pennington
Impact in
- Artificial Intelligence top 0.01%
- Topic Modeling
- Natural Language Processing Techniques
- Sentiment Analysis and Opinion Mining
- Advanced Text Analysis Techniques
- Text and Document Classification Technologies
- Domain Adaptation and Few-Shot Learning
-
- Multimodal Machine Learning Applications
- Advanced Image and Video Retrieval Techniques
Papers in
-
- Neural Networks and Applications 11
- Gaussian Processes and Bayesian Inference 10
- Machine Learning and Data Classification 6
- Machine Learning and ELM 4
- Stochastic Gradient Optimization Techniques 4
- Topic Modeling 3
-
- Random Matrices and Applications 4
- Co-authors
- Richard SocherChristopher D. ManningEric HuangAndrew Y. NgYasaman BahriJascha Sohl‐DicksteinSamuel S. SchoenholzClaude Duhr
- Journals
- Journal of Physics A Mathematical and Theoretical (3 papers)Mathematical Programming (1 paper)The Astrophysical Journal (1 paper)Annual Review of Condensed Matter Physics (1 paper)Journal of High Energy Physics (1 paper)
- Partner nations
- United StatesSwitzerlandCanada
In The Last Decade
Jeffrey Pennington
29 papers receiving 18.6k citations
Hit Papers
Peers
Comparison fields: 5 of 193
- Artificial Intelligence 16.0k
- Computer Vision and Pattern Recognition 3.8k
- Information Systems 3.1k
- General Social Sciences 304
- Signal Processing 969
Countries citing papers authored by Jeffrey Pennington
This map shows the geographic impact of Jeffrey Pennington's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Jeffrey Pennington with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Jeffrey Pennington more than expected).
Fields of papers citing papers by Jeffrey Pennington
This network shows the impact of papers produced by Jeffrey Pennington. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Jeffrey Pennington. The network helps show where Jeffrey Pennington may publish in the future.
Co-authors
The 25 scholars most cited alongside Jeffrey Pennington, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.
All Works
| # | Work | ||
|---|---|---|---|
| 1 | 2024 | 2 | |
| 2 | 2024 | 0 | |
| 3 | 2023 | 0 | |
| 4 | Overparameterization Improves Robustness to Covariate Shift in High Dimensions | 2021 | 8 |
| 5 | Finite Versus Infinite Neural Networks: an Empirical Study | 2020 | 5 |
| 6 | A Mean Field Theory of Batch Normalization | 2019 | 13 |
| 7 | KAMA-NNs: low-dimensional rotation based neural networks | 2019 | 1 |
| 8 | Disentangling Trainability and Generalization in Deep Learning | 2019 | 7 |
| 9 | The Dynamics of Signal Propagation in Gated Recurrent Neural Networks | 2019 | 1 |
| 10 | Dynamical Isometry and a Mean Field Theory of RNNs: Gating Enables Signal Propagation in Recurrent Neural Networks | 2018 | 22 |
| 11 | The Emergence of Spectral Universality in Deep Networks | 2018 | 7 |
| 12 | Sensitivity and Generalization in Neural Networks: an Empirical Study | 2018 | 18 |
| 13 | Bayesian Convolutional Neural Networks with Many Channels are Gaussian Processes. | 2018 | 5 |
| 14 | Deep Neural Networks as Gaussian Processes | 2018 | 76 |
| 15 | The Spectrum of the Fisher Information Matrix of a Single-Hidden-Layer Neural Network | 2018 | 12 |
| 16 | Geometry of neural network loss surfaces via random matrix theory | 2017 | 22 |
| 17 | Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practice | 2017 | 24 |
| 18 | Spherical Random Features for polynomial kernels | 2015 | 21 |
| 19 | Glove: Global Vectors for Word Representation Hit paper breakdown → | 2014 | 18614 |
| 20 | Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions Hit paper breakdown → | 2011 | 743 |
About Jeffrey Pennington
Jeffrey Pennington is a scholar working on Artificial Intelligence, Statistics and Probability, Statistical and Nonlinear Physics, Nuclear and High Energy Physics and Algebra and Number Theory, having authored 33 papers that have together received 20.0k indexed citations. Recurring topics across this work include Neural Networks and Applications (11 papers), Gaussian Processes and Bayesian Inference (10 papers), Machine Learning and Data Classification (6 papers), Black Holes and Theoretical Physics (5 papers), Random Matrices and Applications (4 papers), Machine Learning and ELM (4 papers), Stochastic Gradient Optimization Techniques (4 papers) and Topic Modeling (3 papers). The work is most often cited by research in Artificial Intelligence (16.0k citations), Computer Vision and Pattern Recognition (3.8k citations), Information Systems (3.1k citations), General Social Sciences (304 citations) and Signal Processing (969 citations). Jeffrey Pennington has collaborated with scholars based in United States, Switzerland and Canada. Frequent co-authors include Richard Socher, Christopher D. Manning, Eric Huang, Andrew Y. Ng, Yasaman Bahri, Jascha Sohl‐Dickstein, Samuel S. Schoenholz, Claude Duhr, Surya Ganguli and Lance J. Dixon. Their work appears in journals such as Journal of Physics A Mathematical and Theoretical, Mathematical Programming, The Astrophysical Journal, Annual Review of Condensed Matter Physics and Journal of High Energy Physics.
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.