Decebal Constantin Mocanu

Artificial Intelligence · 2013–2021

A researcher in the Science corpus: 11 papers; trusts 382 researchers and is trusted by 13 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 163 citations into it; #13,972 of 35,345 by trust here, #10,207 by citations
• Computer Vision and Pattern Recognition — 127 citations into it; #19,449 of 21,575 by trust here, #13,542 by citations
• Efficiency & Compression — 51 citations into it
• Probabilistic & Bayesian Methods — 34 citations into it
• Reinforcement Learning — 33 citations into it
• Statistical and Nonlinear Physics — 25 citations into it
• Optimization & Training — 24 citations into it; #2,538 of 2,601 by trust here, #1,349 by citations
• Model Architectures — 23 citations into it; #2,158 of 2,278 by trust here, #1,352 by citations

Whom Decebal Constantin Mocanu trusts overall

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

1. Geoffrey E. Hinton
2. Yoshua Bengio
3. Ruslan Salakhutdinov
4. Alex Krizhevsky
5. Yann LeCun
6. Paul Smolensky
7. Kaiming He
8. Tijmen Tieleman
9. Hugo Larochelle
10. Diederik P. Kingma

Who trusts Decebal Constantin Mocanu overall

1. Ghada Sokar
2. Shiwei Liu
3. Utku Evci
4. Mykola Pechenizkiy
5. Rahul Ramesh
6. William Grant Hatcher
7. Tim Dettmers
8. Hesham Mostafa
9. Wei Yu
10. Tameem Adel

Papers from Decebal Constantin Mocanu's perspective

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

1. ImageNet classification with deep convolutional neural networks
2. Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
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. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. Learning Multiple Layers of Features from Tiny Images
10. ImageNet Large Scale Visual Recognition Challenge

Their papers

• Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science (2017) — 750 citations
• Online Contrastive Divergence with Generative Replay: Experience Replay without Storing Data (2016) — 27 citations
• Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training (2021) — 151 citations
• Automatically Mapped Transfer between Reinforcement Learning Tasks via Three-Way Restricted Boltzmann Machines (2013) — 26 citations
• On-Line Building Energy Optimization Using Deep Reinforcement Learning (2017) — 552 citations
• Big IoT data mining for real-time energy disaggregation in buildings (2016) — 42 citations
• SpaceNet: Make Free Space For Continual Learning (2020) — 92 citations
• Sparse evolutionary deep learning with over one million artificial neurons on commodity hardware (2019) — 95 citations
• A topological insight into restricted Boltzmann machines (2016) — 102 citations
• Deep learning for objective quality assessment of 3D images (2014) — 38 citations
• An automated measure of MDP similarity for transfer in reinforcement learning (2014) — 103 citations