World's Best Scientists 2026 revealed!

D-Index & Metrics

Computer Science

D-Index
107
Citations
37941
World Ranking
267
National Ranking
146

Research.com Recognitions

  • 1996 - IEEE Fellow For contributions to logic synthesis and computer-aided design; specifically for the development of algorithms for the optimization of area, delay, testability, and power of digital circuits.

Overview

Kurt Keutzer is affiliated with the University of California, Berkeley in the United States. Their research primarily focuses on computer science, with extensive work in artificial intelligence, computer vision and pattern recognition, signal processing, electrical and electronic engineering, and computer networks and communications.

The main topics of their research include domain adaptation and few-shot learning, advanced neural network applications, multimodal machine learning applications, topic modeling, natural language processing techniques, advanced image and video retrieval techniques, and speech recognition and synthesis.

Keutzer has published numerous papers in respected academic venues. Some recent notable publications are:

  • "Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT" (2020) in the Proceedings of the AAAI Conference on Artificial Intelligence
  • "Visual Transformers: Token-based Image Representation and Processing for Computer Vision" (2020) in arXiv (Cornell University)
  • "A Review of Single-Source Deep Unsupervised Visual Domain Adaptation" (2020) in IEEE Transactions on Neural Networks and Learning Systems
  • "Multi-Source Distilling Domain Adaptation" (2020) in the Proceedings of the AAAI Conference on Artificial Intelligence
  • "ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning" (2021) in the Proceedings of the AAAI Conference on Artificial Intelligence

Keutzer frequently publishes in venues such as arXiv (Cornell University), Proceedings of the AAAI Conference on Artificial Intelligence, and IEEE conferences including the Winter Conference on Applications of Computer Vision and the International Conference on Computer Vision.

  • arXiv (Cornell University)
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)
  • 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
  • IEEE Transactions on Neural Networks and Learning Systems

Among frequent co-authors are Amir Gholami, Michael W. Mahoney, Chenfeng Xu, Masayoshi Tomizuka, and Shanghang Zhang.

  • Amir Gholami
  • Michael W. Mahoney
  • Chenfeng Xu
  • Masayoshi Tomizuka
  • Shanghang Zhang

Kurt Keutzer was named IEEE Fellow in 1996 for contributions to logic synthesis and computer-aided design, including the development of algorithms for the optimization of area, delay, testability, and power of digital circuits.

Best Publications

  • Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge

    Spyridon Bakas;Mauricio Reyes;Andras Jakab;Stefan Bauer

  • System-level design: orthogonalization of concerns and platform-based design

    K. Keutzer;A.R. Newton;J.M. Rabaey;A. Sangiovanni-Vincentelli

  • FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search

    Bichen Wu;Kurt Keutzer;Xiaoliang Dai;Peizhao Zhang

  • SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud

    Bichen Wu;Alvin Wan;Xiangyu Yue;Kurt Keutzer

  • A Survey of Quantization Methods for Efficient Neural Network Inference

    Amir Gholami;Sehoon Kim;Zhen Dong;Zhewei Yao

  • DAGON: Technology Binding and Local Optimization by DAG Matching

    K. Keutzer

  • DenseNet: Implementing Efficient ConvNet Descriptor Pyramids

    Forrest N. Iandola;Matthew W. Moskewicz;Sergey Karayev;Ross B. Girshick

  • Estimation of average switching activity in combinational and sequential circuits

    A. Ghosh;S. Devadas;K. Keutzer;J. White

  • SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud

    Bichen Wu;Xuanyu Zhou;Sicheng Zhao;Xiangyu Yue

  • SqueezeDet: Unified, Small, Low Power Fully Convolutional Neural Networks for Real-Time Object Detection for Autonomous Driving

    Bichen Wu;Forrest Iandola;Peter H. Jin;Kurt Keutzer

  • Dense point trajectories by GPU-accelerated large displacement optical flow

    Narayanan Sundaram;Thomas Brox;Kurt Keutzer

  • Fast support vector machine training and classification on graphics processors

    Bryan Catanzaro;Narayanan Sundaram;Kurt Keutzer

  • Addressing the system-on-a-chip interconnect woes through communication-based design

    M. Sgroi;M. Sheets;A. Mihal;K. Keutzer

  • Large Batch Optimization for Deep Learning: Training BERT in 76 minutes

    Yang You;Jing Li;Sashank Reddi;Jonathan Hseu

  • Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT

    Sheng Shen;Zhen Dong;Jiayu Ye;Linjian Ma

  • HAWQ: Hessian AWare Quantization of Neural Networks With Mixed-Precision

    Zhen Dong;Zhewei Yao;Amir Gholami;Michael Mahoney

  • ImageNet Training in Minutes

    Yang You;Zhao Zhang;Cho-Jui Hsieh;James Demmel

  • Getting to the bottom of deep submicron

    Dennis Sylvester;Kurt Keutzer

  • Shift: A Zero FLOP, Zero Parameter Alternative to Spatial Convolutions

    Bichen Wu;Alvin Wan;Xiangyu Yue;Peter Jin

  • SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation

    Chenfeng Xu;Bichen Wu;Zining Wang;Wei Zhan

  • Visual Transformers: Token-based Image Representation and Processing for Computer Vision

    Bichen Wu;Chenfeng Xu;Xiaoliang Dai;Alvin Wan

  • FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search

    Bichen Wu;Xiaoliang Dai;Peizhao Zhang;Yanghan Wang

Frequent Co-Authors

Sicheng Zhao
Sicheng Zhao Tsinghua University
Michael W. Mahoney
Michael W. Mahoney University of California, Berkeley
Sharad Malik
Sharad Malik Princeton University
James Demmel
James Demmel University of California, Berkeley
Alberto Sangiovanni-Vincentelli
Alberto Sangiovanni-Vincentelli University of California, Berkeley
Joseph E. Gonzalez
Joseph E. Gonzalez University of California, Berkeley
Bryan Catanzaro
Bryan Catanzaro Nvidia (United States)
Cho-Jui Hsieh
Cho-Jui Hsieh University of California, Los Angeles
Nadathur Satish
Nadathur Satish Facebook (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

If you’re interested in studying Computer Science in the USA, there are several flexible online degree options and fast-track career pathways to consider. Many students explore related fields such as business or artificial intelligence to expand their career opportunities and skillsets.

For those aiming for leadership roles, pursuing a cheap mba online can be an affordable way to gain business acumen alongside technical expertise. If you’re looking to complete your education quickly, consider the advantages of 1 year masters programs, which enable you to enter the workforce faster without compromising on quality.

Interested in shorter programs that lead to high salaries? Explore short careers that pay well, which can help you gain a solid footing in the technology sector without years of study. Meanwhile, those focused on cutting-edge tech should look into online degrees in ai to acquire highly sought-after skills in machine learning and automation.

Best Scientists Citing Kurt Keutzer

Trending Scientists