Erich Elsen
Artificial Intelligence · with Simonyan · 2014–2022
A researcher in the Science corpus: 24 papers; trusts 1,316 researchers and is trusted by 792 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 635 citations into it; #1,393 of 36,961 by trust here, #371 by citations
- Computer Vision and Pattern Recognition — 383 citations into it; #2,577 of 21,973 by trust here, #1,322 by citations
- Natural Language Processing — 173 citations into it; #3,349 of 5,725 by trust here, #261 by citations
- Model Architectures — 149 citations into it; #2,125 of 2,288 by trust here, #1,236 by citations
- Efficiency & Compression — 136 citations into it; #135 of 1,273 by trust here, #232 by citations
- Signal Processing — 125 citations into it; #448 of 7,592 by trust here, #84 by citations
- Optimization & Training — 120 citations into it; #1,739 of 2,605 by trust here, #373 by citations
- Generative Models — 108 citations into it; #345 of 1,963 by trust here, #225 by citations
Whom Erich Elsen trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Diederik P. Kingma
- Alex Krizhevsky
- Kaiming He
- Ilya Sutskever
- Yoshua Bengio
- Yann LeCun
- Alex Graves
- Karen Simonyan
- Christian Szegedy
Who trusts Erich Elsen overall
- Sara Hooker
- Yu Zhang
- Trevor Gale
- Xu Tan
- Ye Jia
- Dan Alistarh
- Elias Frantar
- Jonathan Frankle
- Heiga Zen
- Ron J. Weiss
Papers from Erich Elsen's perspective
Ordered by how strongly the researchers Erich Elsen 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)
- Going deeper with convolutions
- Learning Multiple Layers of Features from Tiny Images
Their papers
- Scaling Language Models: Methods, Analysis & Insights from Training Gopher (2021) — 1,640 citations
- Training Compute-Optimal Large Language Models (2022) — 3,535 citations
- Deep Speech 2 : End-to-End Speech Recognition in English and Mandarin (2015) — 3,177 citations
- Deep Speech: Scaling up end-to-end speech recognition (2014) — 2,263 citations
- Mixed Precision Training (2017) — 2,457 citations
- Improving language models by retrieving from trillions of tokens (2021) — 1,785 citations
- Parallel WaveNet: Fast High-Fidelity Speech Synthesis (2017) — 912 citations
- The State of Sparsity in Deep Neural Networks (2019) — 891 citations
- Efficient Neural Audio Synthesis (2018) — 936 citations
- Rigging the Lottery: Making All Tickets Winners (2019) — 758 citations
- Exploring Sparsity in Recurrent Neural Networks (2017) — 328 citations
- Enabling Factorized Piano Music Modeling and Generation with the MAESTRO Dataset (2018) — 596 citations
- DSD: Regularizing Deep Neural Networks with Dense-Sparse-Dense Training Flow (2016) — 83 citations
- High Fidelity Speech Synthesis with Adversarial Networks (2019) — 264 citations
- Persistent RNNs: Stashing Recurrent Weights On-Chip (2016) — 95 citations
- Unified Scaling Laws for Routed Language Models (2022) — 285 citations
- Step-unrolled Denoising Autoencoders for Text Generation (2021) — 152 citations
- Onsets and Frames: Dual-Objective Piano Transcription (2017) — 335 citations
- Fast Sparse ConvNets (2019) — 161 citations
- End-to-End Adversarial Text-to-Speech (2020) — 197 citations