World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
39
Citations
149117
World Ranking
9453
National Ranking
3998

Overview

Dumitru Erhan is affiliated with Google in the United States and has contributed to the field of computer science with a focus on artificial intelligence and related subfields. Their research spans multiple areas including computer vision, reinforcement learning, and neural dynamics.

Their body of work includes publications primarily in well-known venues such as arXiv (Cornell University) and Leibniz-Zentrum für Informatik (Schloss Dagstuhl). The following is a selection of notable papers authored or coauthored by them, reflecting their research interests and outputs:

  • Static Analysis of Shape in TensorFlow Programs, 2020, arXiv (Cornell University)
  • Can We Trust AI-Powered Real-Time Embedded Systems? (Invited Paper), 2022, Leibniz-Zentrum für Informatik (Schloss Dagstuhl)
  • Phenaki: Variable Length Video Generation From Open Domain Textual Description, 2022, arXiv (Cornell University)
  • FitVid: Overfitting in Pixel-Level Video Prediction, 2021, arXiv (Cornell University)
  • SurfelGAN: Synthesizing Realistic Sensor Data for Autonomous Driving, 2020, arXiv (Cornell University)

Their research covers the following main fields of study:

  • Computer Science

Within this, their specific subfields of study include:

  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Cognitive Neuroscience
  • Statistical and Nonlinear Physics
  • Computer Graphics and Computer-Aided Design

Their research topics reflect an interdisciplinary approach, integrating machine learning with applications in robotics and video analysis. Key topics they have worked on include:

  • Machine Learning and Data Classification
  • Generative Adversarial Networks and Image Synthesis
  • Reinforcement Learning in Robotics
  • Neural dynamics and brain function
  • Video Analysis and Summarization
  • Computational Physics and Python Applications
  • Machine Learning and Algorithms

The scientist has collaborated frequently with several coauthors, among whom the most frequent are:

  • Mohammad Babaeizadeh
  • Mohammad Saffar
  • Sergey Levine
  • Chelsea Finn
  • Danijar Hafner

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

  • Intriguing properties of neural networks

    Christian Szegedy;Wojciech Zaremba;Ilya Sutskever;Joan Bruna

  • Show and tell: A neural image caption generator

    Oriol Vinyals;Alexander Toshev;Samy Bengio;Dumitru Erhan

  • Why Does Unsupervised Pre-training Help Deep Learning?

    Dumitru Erhan;Aaron C. Courville;Yoshua Bengio;Pascal Vincent

  • Theano: A Python framework for fast computation of mathematical expressions

    Rami Al-Rfou;Guillaume Alain;Amjad Almahairi

  • Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks

    Konstantinos Bousmalis;Nathan Silberman;David Dohan;Dumitru Erhan

  • Why Does Unsupervised Pre-training Help Deep Learning?

    Dumitru Erhan;Yoshua Bengio;Aaron Courville;Pierre-Antoine Manzagol

  • Challenges in Representation Learning: A Report on Three Machine Learning Contests

    Ian J. Goodfellow;Dumitru Erhan;Pierre Luc Carrier;Aaron Courville

  • 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

  • An empirical evaluation of deep architectures on problems with many factors of variation

    Hugo Larochelle;Dumitru Erhan;Aaron Courville;James Bergstra

  • Domain separation networks

    Konstantinos Bousmalis;George Trigeorgis;Nathan Silberman;Dilip Krishnan

  • Show and Tell: Lessons Learned from the 2015 MSCOCO Image Captioning Challenge

    Oriol Vinyals;Alexander Toshev;Samy Bengio;Dumitru Erhan

  • TRAINING DEEP NEURAL NETWORKS ON NOISY LABELS WITH BOOTSTRAPPING

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

  • The (Un)reliability of saliency methods

    Pieter-Jan Kindermans;Sara Hooker;Julius Adebayo;Maximilian Alber

  • The Difficulty of Training Deep Architectures and the Effect of Unsupervised Pre-Training

    Dumitru Erhan;Pierre-Antoine Manzagol;Yoshua Bengio;Samy Bengio

  • Model-Based Reinforcement Learning for Atari

    Lukasz Kaiser;Mohammad Babaeizadeh;Piotr Milos;Blazej Osinski

  • Challenges in representation learning

    Ian J. Goodfellow;Dumitru Erhan;Pierre Luc Carrier;Aaron Courville

  • Scalable, high-quality object detection

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

  • A Benchmark for Interpretability Methods in Deep Neural Networks

    Sara Hooker;Dumitru Erhan;Pieter-Jan Kindermans;Been Kim

  • Model Based Reinforcement Learning for Atari

    Łukasz Kaiser;Mohammad Babaeizadeh;Piotr Miłos;Błażej Osiński

Frequent Co-Authors

Christian Szegedy
Christian Szegedy Google (United States)
Yoshua Bengio
Yoshua Bengio University of Montreal
Chelsea Finn
Chelsea Finn Stanford University
Sergey Levine
Sergey Levine University of California, Berkeley
Alexander Toshev
Alexander Toshev Apple (United States)
Honglak Lee
Honglak Lee University of Michigan–Ann Arbor
Aaron Courville
Aaron Courville University of Montreal
Been Kim
Been Kim Google (United States)
Ian Goodfellow
Ian Goodfellow Google (United States)

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 Computer Science in the USA unlocks a range of related online degrees and career pathways for students and professionals at every stage. For those interested in data analysis and artificial intelligence, pursuing a data science degree can be a strategic choice, with many affordable programs now available online.

Technical roles continue to evolve rapidly. Specialized programs like an online master’s in electrical engineering degree offer advanced knowledge and often lead to high-growth, in-demand careers in areas such as robotics, telecommunications, and green energy.

For those seeking quicker entry or advancement, there are many quick certifications that pay well. These can fast-track your career without the time and financial commitment of a full degree.

Additionally, if time is a crucial factor, you can explore options like the shortest master degree programs to gain advanced credentials faster and begin your next chapter sooner.

Best Scientists Citing Dumitru Erhan

Trending Scientists