David Sussillo
Artificial Intelligence · 2009–2022
A researcher in the Science corpus: 14 papers; trusts 636 researchers and is trusted by 110 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 240 citations into it; #3,141 of 36,961 by trust here, #4,491 by citations
- Cognitive Neuroscience — 128 citations into it; #348 of 11,026 by trust here, #812 by citations
- Computer Vision and Pattern Recognition — 105 citations into it
- Model Architectures — 73 citations into it; #1,914 of 2,288 by trust here, #1,305 by citations
- Natural Language Processing — 73 citations into it; #3,936 of 5,725 by trust here, #2,042 by citations
- Cellular and Molecular Neuroscience — 41 citations into it
- Electrical and Electronic Engineering — 31 citations into it; #305 of 16,595 by trust here, #4,333 by citations
- Optimization & Training — 25 citations into it; #1,585 of 2,605 by trust here, #1,989 by citations
Whom David Sussillo trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- James Martens
- Yoshua Bengio
- Ilya Sutskever
- Geoffrey E. Hinton
- Alex Graves
- Sepp Hochreiter
- Diederik P. Kingma
- David E. Rumelhart
- Dzmitry Bahdanau
- Alex Krizhevsky
Who trusts David Sussillo overall
- Guangyu Robert Yang
- H. Francis Song
- Rafael Yuste
- John P. Cunningham
- Xiao-Jing Wang
- Mantas Lukosevicius
- Lea Duncker
- Kohei Nakajima
- Saurabh Saxena
- Omri Barak
Papers from David Sussillo's perspective
Ordered by how strongly the researchers David Sussillo 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
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
- Learning Multiple Layers of Features from Tiny Images
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
Their papers
- Capacity and Trainability in Recurrent Neural Networks (2016) — 215 citations
- Hallucinations in Neural Machine Translation (2018) — 183 citations
- A Neural Transducer (2015) — 49 citations
- An Online Sequence-to-Sequence Model Using Partial Conditioning (2015) — 114 citations
- Generating Coherent Patterns of Activity from Chaotic Neural Networks (2009) — 1,136 citations
- Random Walk Initialization for Training Very Deep Feedforward Networks (2014) — 82 citations
- Opening the Black Box: Low-Dimensional Dynamics in High-Dimensional Recurrent Neural Networks (2013) — 562 citations
- Catalyzing next-generation Artificial Intelligence through NeuroAI (2022) — 299 citations
- Organizing recurrent network dynamics by task-computation to enable continual learning (2020) — 98 citations
- Computation Through Neural Population Dynamics (2020) — 657 citations
- A dataset and architecture for visual reasoning with a working memory (2018) — 56 citations
- Inferring single-trial neural population dynamics using sequential auto-encoders (2017) — 800 citations
- Input Switched Affine Networks: An RNN Architecture Designed for Interpretability (2016) — 38 citations
- Context-dependent computation by recurrent dynamics in prefrontal cortex (2013) — 1,875 citations