João Sacramento

Artificial Intelligence · 2018–2022

A researcher in the Science corpus: 8 papers; trusts 402 researchers and is trusted by 38 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 281 citations into it
• Computer Vision and Pattern Recognition — 168 citations into it
• Optimization & Training — 84 citations into it
• Cognitive Neuroscience — 68 citations into it; #4,820 of 10,852 by trust here, #5,528 by citations
• Meta & Continual Learning — 62 citations into it; #161 of 1,041 by trust here, #226 by citations
• Probabilistic & Bayesian Methods — 58 citations into it
• Representation & Self-Supervised Learning — 53 citations into it
• Model Architectures — 46 citations into it

Whom João Sacramento trusts overall

Their strongest outbound trust, strongest first, inferred from their citations.

1. Geoffrey E. Hinton
2. Yoshua Bengio
3. Diederik P. Kingma
4. Alex Krizhevsky
5. Yann LeCun
6. Kaiming He
7. J. Urgen Schmidhuber
8. Max Welling
9. Ilya Sutskever
10. Radford M. Neal

Who trusts João Sacramento overall

1. Gyuhak Kim
2. Guangyu Robert Yang
3. James C. R. Whittington
4. Arild Nøkland
5. Christian Henning
6. Zixuan Ke
7. Yiduo Guo
8. James Smith
9. Rafal Bogacz
10. Xiao-Jing Wang

Papers from João Sacramento's perspective

Ordered by how strongly the researchers João Sacramento trusts endorse each paper. Same corpus, a different order for every researcher.

1. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
2. ImageNet classification with deep convolutional neural networks
3. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
4. Gradient-based learning applied to document recognition
5. Long Short-Term Memory
6. Attention is All you Need (Neural Information Processing Systems)
7. ImageNet: A large-scale hierarchical image database
8. Learning Multiple Layers of Features from Tiny Images
9. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
10. ImageNet Large Scale Visual Recognition Challenge

Their papers

• Learning where to learn: Gradient sparsity in meta and continual learning (2021) — 60 citations
• Posterior Meta-Replay for Continual Learning (2021) — 76 citations
• Dendritic cortical microcircuits approximate the backpropagation algorithm (2018) — 373 citations
• A deep learning framework for neuroscience (2019) — 1,016 citations
• Transformers learn in-context by gradient descent (2022) — 821 citations
• Neural networks with late-phase weights (2020) — 40 citations
• Continual learning with hypernetworks (2019) — 428 citations
• Approximating the Predictive Distribution via Adversarially-Trained Hypernetworks (2018)