Michael Chang

Artificial Intelligence · 2016–2023

A researcher in the Science corpus: 8 papers; trusts 440 researchers and is trusted by 476 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 255 citations into it; #4,225 of 35,345 by trust here, #3,783 by citations
• Computer Vision and Pattern Recognition — 151 citations into it; #1,939 of 21,575 by trust here, #2,768 by citations
• Reinforcement Learning — 109 citations into it
• Model Architectures — 62 citations into it
• Representation & Self-Supervised Learning — 43 citations into it; #736 of 3,145 by trust here, #596 by citations
• Natural Language Processing — 36 citations into it
• Control and Systems Engineering — 26 citations into it
• Generative Models — 25 citations into it

Whom Michael Chang trusts overall

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

1. Geoffrey E. Hinton
2. Diederik P. Kingma
3. Alex Graves
4. Yoshua Bengio
5. J. Urgen Schmidhuber
6. Ilya Sutskever
7. Alex Krizhevsky
8. Yann LeCun
9. Ruslan Salakhutdinov
10. Jimmy Ba

Who trusts Michael Chang overall

1. Sjoerd van Steenkiste
2. Arslan Chaudhry
3. Jiajun Wu
4. J. Urgen Schmidhuber
5. Peter W. Battaglia
6. Jorge Armando Mendez Mendez
7. Josh Tenenbaum
8. Anirudh Goyal
9. Yoshua Bengio
10. Eric Crawford

Papers from Michael Chang's perspective

Ordered by how strongly the researchers Michael Chang 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. Long Short-Term Memory
5. Attention is All you Need (Neural Information Processing Systems)
6. Gradient-based learning applied to document recognition
7. ImageNet: A large-scale hierarchical image database
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
10. Learning Multiple Layers of Features from Tiny Images

Their papers

• A Compositional Object-Based Approach to Learning Physical Dynamics (2016) — 470 citations
• Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions (2018) — 302 citations
• Understanding Visual Concepts with Continuation Learning (2016) — 55 citations
• Entity Abstraction in Visual Model-Based Reinforcement Learning (2019) — 208 citations
• Automatically Composing Representation Transformations as a Means for Generalization (2018) — 80 citations
• Doing more with less: meta-reasoning and meta-learning in humans and machines (2019) — 134 citations
• MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies (2019) — 230 citations
• Human-Timescale Adaptation in an Open-Ended Task Space (2023) — 163 citations