Lukasz Romaszko

Computer Vision and Pattern Recognition · 2013–2017

A researcher in the Science corpus: 4 papers; trusts 31 researchers and is trusted by 0 researchers here, as inferred from the citation graph.

Subfields

• Computer Vision and Pattern Recognition — 23 citations into it
• Artificial Intelligence — 18 citations into it
• Optimization & Training — 9 citations into it
• Model Architectures — 5 citations into it

Whom Lukasz Romaszko trusts overall

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

1. Radford M. Neal
2. Diederik P. Kingma
3. Dana H. Ballard
4. Karen Simonyan
5. Geoffrey E. Hinton
6. Andrew Zisserman
7. Jimmy Ba
8. Mengye Ren
9. Matthew Maverick Loper
10. Alex Krizhevsky

Who trusts Lukasz Romaszko overall

1. Klaus Greff
2. Abhijit Kundu
3. L. Eon Bottou
4. Alireza Zareian
5. Sjoerd van Steenkiste
6. Yin Li
7. Martín Arjovsky
8. Haoxuan You

Papers from Lukasz Romaszko's perspective

Ordered by how strongly the researchers Lukasz Romaszko 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. ImageNet: A large-scale hierarchical image database
6. Attention is All you Need (Neural Information Processing Systems)
7. Long Short-Term Memory
8. Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
9. GENERATIVE ADVERSARIAL NETS
10. Learning Multiple Layers of Features from Tiny Images

Their papers

• Challenges in representation learning: A report on three machine learning contests (2013) — 2,020 citations
• Vision-as-Inverse-Graphics: Obtaining a Rich 3D Explanation of a Scene from a Single Image (2017) — 46 citations
• A Deep Learning Approach with an Ensemble-Based Neural Network Classifier for Black Box ICML 2013 Contest (2013) — 7 citations
• A brief Review of the ChaLearn AutoML Challenge: Any-time Any-dataset Learning without Human Intervention (2016) — 84 citations