World's Best Scientists 2026 revealed!

Overview

Christian Szegedy is a researcher affiliated with Google in the United States. Their expertise lies primarily in computer science, with a strong focus on subfields such as artificial intelligence, computer vision and pattern recognition, information systems, statistical and nonlinear physics, and computational theory and mathematics.

Their research covers a variety of main topics including topic modeling, natural language processing techniques, neural networks and applications, machine learning and data classification, multimodal machine learning applications, software engineering research, as well as logic, programming, and type systems.

Notable recent publications by Christian Szegedy include:

  • Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift, 2024, arXiv (Cornell University)
  • Can We Trust AI-Powered Real-Time Embedded Systems? (Invited Paper), 2022, Leibniz-Zentrum für Informatik (Schloss Dagstuhl)
  • Autoformalization with Large Language Models, 2022, arXiv (Cornell University)
  • Memorizing Transformers, 2022, arXiv (Cornell University)
  • Hierarchical Transformers Are More Efficient Language Models, 2022, Findings of the Association for Computational Linguistics: NAACL 2022

The researcher collaborates frequently with several co-authors, including Yuhuai Wu, Markus N. Rabe, Piotr Nawrot, Szymon Tworkowski, and Michał Tyrolski.

Christian Szegedy's work has been published repeatedly in venues such as arXiv (Cornell University), Leibniz-Zentrum für Informatik (Schloss Dagstuhl), Findings of the Association for Computational Linguistics: NAACL 2022, Proceedings of the AAAI Conference on Artificial Intelligence, and Zenodo (CERN European Organization for Nuclear Research).

Best Publications

  • Going deeper with convolutions

    Christian Szegedy;Wei Liu;Yangqing Jia;Pierre Sermanet

  • SSD: Single Shot MultiBox Detector

    Wei Liu;Dragomir Anguelov;Dumitru Erhan;Christian Szegedy

  • Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

    Sergey Ioffe;Christian Szegedy

  • Rethinking the Inception Architecture for Computer Vision

    Christian Szegedy;Vincent Vanhoucke;Sergey Ioffe;Jon Shlens

  • Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning

    Christian Szegedy;Sergey Ioffe;Vincent Vanhoucke;Alexander A Alemi

  • Explaining and Harnessing Adversarial Examples

    Ian J. Goodfellow;Jonathon Shlens;Christian Szegedy

  • Intriguing properties of neural networks

    Christian Szegedy;Wojciech Zaremba;Ilya Sutskever;Joan Bruna

  • DeepPose: Human Pose Estimation via Deep Neural Networks

    Alexander Toshev;Christian Szegedy

  • Deep Neural Networks for Object Detection

    Christian Szegedy;Alexander Toshev;Dumitru Erhan

  • Scalable Object Detection Using Deep Neural Networks

    Dumitru Erhan;Christian Szegedy;Alexander Toshev;Dragomir Anguelov

  • TRAINING DEEP NEURAL NETWORKS ON NOISY LABELS WITH BOOTSTRAPPING

    Scott E. Reed;Honglak Lee;Dragomir Anguelov;Christian Szegedy

  • Scalable, high-quality object detection

    Christian Szegedy;Scott E. Reed;Dumitru Erhan;Dragomir Anguelov

  • DeepMath - Deep Sequence Models for Premise Selection

    Alex A. Alemi;Francois Chollet;Niklas Een;Geoffrey Irving

  • DeepMath - Deep Sequence Models for Premise Selection

    Alexander A. Alemi;François Chollet;Geoffrey Irving;Christian Szegedy

  • Deep Network Guided Proof Search

    Sarah M. Loos;Geoffrey Irving;Christian Szegedy;Cezary Kaliszyk

  • Object detection using deep neural networks

    Christian Szegedy;Dumitru Erhan;Alexander Toshkov Toshev

  • HOList: An Environment for Machine Learning of Higher Order Logic Theorem Proving

    Kshitij Bansal;Sarah Loos;Markus Rabe;Christian Szegedy

  • Modular code generation from synchronous block diagrams: modularity vs. code size

    Roberto Lublinerman;Christian Szegedy;Stavros Tripakis

  • Graph Representations for Higher-Order Logic and Theorem Proving

    Aditya Paliwal;Sarah M. Loos;Markus N. Rabe;Kshitij Bansal

  • HolStep: A Machine Learning Dataset for Higher-order Logic Theorem Proving

    Cezary Kaliszyk;Francois Chollet;Christian Szegedy

Frequent Co-Authors

Dumitru Erhan
Dumitru Erhan Google (United States)
Vincent Vanhoucke
Vincent Vanhoucke Google (United States)
Alexander Toshev
Alexander Toshev Apple (United States)
Ian Goodfellow
Ian Goodfellow Google (United States)
Jonathon Shlens
Jonathon Shlens Google (United States)
Rob Fergus
Rob Fergus New York University
Josef Urban
Josef Urban Czech Technical University in Prague

If you think any of the details on this page are incorrect, let us know.

Report an issue

We appreciate your kind effort to assist us to improve this page, it would be helpful providing us with as much detail as possible in the text box below:

Related Online Degrees & Career Pathways

Exploring online degrees opens flexible pathways for those interested in computer science and related fields. Many college with low gpa options are now available, making higher education more accessible to students with diverse academic backgrounds.

For those seeking rapid career entry, consider enrolling in a fastest computer science degree program, which allows you to earn your degree in less time compared to traditional formats.

If you’re interested in the intersection of technology and the environment, exploring online environmental engineering degree science and engineering programs can lead to rewarding roles in sustainability and engineering. Graduates can pursue a wide range of positions—find out more about what can you do with an environmental studies degree to broaden your potential career opportunities in the field.

Whether you're looking to accelerate your studies, seek affordable options, or apply your skills across multiple disciplines, there are diverse routes to consider as you plan your next steps in computer science and beyond.

Best Scientists Citing Christian Szegedy

Trending Scientists

Recently Published Articles