Prof. Vivienne Sze

Associate Professor of Electrical Engineering and Computer Science

Primary DLC

Microsystems Technology Laboratories

MIT Room: 38-260

Assistant

Janice Balzer
balzer@mit.edu

Areas of Interest and Expertise

Joint Design of Algorithms, Architectures, VLSI and Systems for Energy Efficient Implementations
Applications Include Computer Vision, Machine Learning, Autonomous Navigation, Robotics, Video Coding/Processing, Health Monitoring and Distributed Sensing
Energy-Efficient Deep Learning
Control and Signal Processing
Computers and Systems
Low Power Processor for Computer Vision and Video Compression

Research Summary

Vivienne Sze, in the Department of Electrical Engineering and Computer Science, focuses her research on designing and implementing computing systems that enable energy-efficient machine learning, computer vision, and video compression for a wide range of applications, including autonomous navigation, digital health, and the internet of things. In particular, she is interested in the joint design of algorithms, architectures, circuits, and systems to enable optimal tradeoffs between energy consumption, speed, and quality of results.

Recent Work

  • Video

    2020 Autonomy Day 2 - Vivienne Sze

    April 9, 2020Conference Video Duration: 29:35

    Computing near the sensor is preferred over the cloud due to privacy and/or latency concerns for a wide range of applications including robotics/drones, self-driving cars, smart Internet of Things, and portable/wearable electronics. However, at the sensor there are often stringent constraints on energy consumption and cost in addition to the throughput and accuracy requirements of the application. In this talk, we will describe how joint algorithm and hardware design can be used to reduce energy consumption while delivering real-time and robust performance for applications including deep learning, computer vision, autonomous navigation/exploration and video/image processing. We will show how energy-efficient techniques that exploit correlation and sparsity to reduce compute, data movement and storage costs can be applied to various tasks including image classification, depth estimation, super-resolution, localization and mapping.

    Vivienne Sze - 2019 RD Conference

    November 20, 2019Conference Video Duration: 37:4

    Efficient Computing for AI and Robotics

    Computing near the sensor is preferred over the cloud due to privacy and/or latency concerns for a wide range of applications including robotics/drones, self-driving cars, smart Internet of Things, and portable/wearable electronics. However, at the sensor there are often stringent constraints on energy consumption and cost in addition to the throughput and accuracy requirements of the application. In this talk, we will describe how joint algorithm and hardware design can be used to reduce energy consumption while delivering real-time and robust performance for applications including deep learning, computer vision, autonomous navigation/exploration and video/image processing. We will show how energy-efficient techniques that exploit correlation and sparsity to reduce compute, data movement and storage costs can be applied to various tasks including image classification, depth estimation, super-resolution, localization and mapping.

    2019 MIT Research and Development Conference