Petko Georgiev

Artificial Intelligence · 2015–2025

A researcher in the Science corpus: 12 papers; trusts 58 researchers and is trusted by 16 researchers here, as inferred from the citation graph.

Subfields

• Artificial Intelligence — 213 citations into it
• Computer Vision and Pattern Recognition — 105 citations into it; #7,686 of 21,575 by trust here, #5,680 by citations
• Reinforcement Learning — 93 citations into it
• Natural Language Processing — 53 citations into it
• Signal Processing — 39 citations into it; #3,609 of 7,572 by trust here, #3,673 by citations
• Model Architectures — 25 citations into it
• Optimization & Training — 15 citations into it
• Experimental and Cognitive Psychology — 12 citations into it

Whom Petko Georgiev trusts overall

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

1. Geoffrey E. Hinton
2. Alex Krizhevsky
3. Yoshua Bengio
4. Diederik P. Kingma
5. Yann LeCun
6. Ilya Sutskever
7. Alex Graves
8. Hong Lu
9. Radford M. Neal
10. Kaiming He

Who trusts Petko Georgiev overall

1. Young Geun Kim
2. Huynh Nguyen Loc
3. Md Maruf Hossain Shuvo
4. Shuochao Yao
5. Shibo Zhang
6. Nils Y. Hammerla
7. He Li
8. Carole-Jean Wu
9. Nicholas Donald Lane
10. Jindong Wang

Papers from Petko Georgiev's perspective

Ordered by how strongly the researchers Petko Georgiev 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. Attention is All you Need (Neural Information Processing Systems)
4. Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
5. Long Short-Term Memory
6. Gradient-based learning applied to document recognition
7. ImageNet: A large-scale hierarchical image database
8. Learning Multiple Layers of Features from Tiny Images
9. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (International Conference on Machine Learning)
10. GENERATIVE ADVERSARIAL NETS

Their papers

• Grandmaster level in StarCraft II using multi-agent reinforcement learning (2019) — 4,437 citations
• StarCraft II: A New Challenge for Reinforcement Learning (2017) — 971 citations
• Imitating Interactive Intelligence (2020) — 74 citations
• A data-driven approach for learning to control computers (2022) — 128 citations
• Intra-agent speech permits zero-shot task acquisition (2022) — 10 citations
• Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context (2024) — 3,818 citations
• Gemma 2: Improving Open Language Models at a Practical Size (2024) — 2,206 citations
• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities (2025) — 3,609 citations
• Accelerating Mobile Audio Sensing Algorithms through On-Chip GPU Offloading (2017) — 22 citations
• DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices (2016) — 568 citations
• DeepEar: robust smartphone audio sensing in unconstrained acoustic environments using deep learning (2015) — 335 citations
• An Early Resource Characterization of Deep Learning on Wearables, Smartphones and Internet-of-Things Devices (2015) — 220 citations