Researcher Kurt Keutzer

Researcher Biography
http://www.eecs.berkeley.edu/Faculty/Homepages/keutzer.html

Current Projects

An Innovative Approach to the Dual Problems of High-Resolution Input and Video Object Detection
Automated Search for Neural Net Architectures
Efficient Model for Large-Scale Point Cloud Perception
Efficient Neural Networks through Systematic Quantization
Embedded natural language processing for in-car speech commands
Enabling Valuable Training Data through Domain Adaptation
Systematic Study of Neural Network Robustness Against Adversarial Attacks
Training Data Augmentation for Autonomous Driving
Unified Neural Architecture Search Framework for Computer Vision
Using High-Level Structure and Context for Object Recognition

Past Projects

Design Space Exploration for Deep Neural Nets for Advanced Driver Assistance Systems
Domain Adaptation for Realistic LiDAR Data Synthesis
Efficient Neural Nets for Real-Time object-recognition on High-Resolution Images
Energy-Efficient Deep Neural Nets for Occupancy-Grid Mapping
Real-time, Energy Efficient Video Object Detection and Tracking
Safe and Effective Learning through Formal Simulation