Energy-Efficient
Multimedia Systems Group

Professor Vivienne Sze

News

Subscribe to our mailing list

7.18.2017
MIT News: Bringing neural networks to cellphones

7.12.2017
MIT News: Miniaturizing the brain of a drone

6.25.2017
Slides from ISCA Tutorial on Hardware Architectures for DNNs now available online

5.9.2017
Zhengdong’s paper on “FAST: A Framework to Accelerate Super-Resolution Processing on Compressed Videos” has been accepted for presentation at the 2017 CVPR Workshop on New Trends in Image Restoration and Enhancement

5.8.2017
James’s paper on “Low Power Depth Estimation for Time-of-Flight Imaging” has been accepted for presentation at ICIP 2017

5.1.2017
Prof. Sze will be teaching a new class on “6.S082/6.888 Hardware Architecture for Deep Learning” in Fall 2017 with Prof. Joel Emer

4.28.2017
Amr and Zhengdong’s paper on “Visual-Inertial Odometry on Chip: An Algorithm-and-Hardware Co-design Approach” has been accepted for presentation at RSS 2017

4.27.2017
Prof. Sze receives the 2017 Qualcomm Faculty Award

3.28.2017
New paper “Efficient Processing of Deep Neural Networks: A Tutorial and Survey” now available on arxiv

3.27.2017
DNN Energy Estimation Website available online

3.26.2017
Mehul’s paper on “A Fully-Integrated Energy-Efficient H.265/HEVC Decoder with eDRAM for Wearable Devices” has been accepted for presentation at IEEE VLSI 2017

3.17.2017
Our paper on “Towards Closing the Energy Gap Between HOG and CNN Features for Embedded Vision” has been accepted for presentation at IEEE ISCAS 2017

3.3.2017
Tien-Ju and Yu-Hsin’s paper “Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning” has been accepted for presentation at IEEE CVPR 2017

2.13.2017
Prof. Sze receives the Google Faculty Research Award

2.7.2017
Prof. Sze promoted to the rank of Associate Professor without Tenure

1.22.2017
We will be giving a tutorial on Hardware Architectures for Deep Neural Networks at ISCA 2017

1.17.2017
Our paper “Hardware for Machine Learning: Challenges and Opportunities” has been accepted for presentation at IEEE CICC 2017

1.3.2017
Amr and Zhengdong’s paper on “A 58.6mW 30fps Real-Time Programmable Multi-Object Detection Accelerator with Deformable Parts Models on Full HD 1920×1080 Videos” has been accepted for publication in the Journal of Solid-State Circuits (JSSC)

12.30.2016
Our paper “Eyeriss: A Spatial Architecture for Energy-Efficient Dataflow for Convolutional Neural Networks” has been selected for IEEE Micro “Top Picks in Computer Architecture” for 2016

12.23.2016
New paper on “Hardware for Machine Learning: Challenges and Opportunities” available on arXiv

12.22.2016
Slides from NIPS 2016 Workshop on EMDNN available online

12.2.2016
Yu-Hsin Chen receives the IEEE Solid-State Circuits Society Predoctoral Achievement Award for 2016-2017

11.16.2016
New paper on “Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning” available on arXiv

11.12.2016
Slides for MICRO Tutorial on Hardware Architectures for DNNs now available online

11.7.2016
Prof. Sze’s talk on “Energy-Efficient Hardware for Embedded Vision and Deep Convolutional Neural Networks” now available on YouTube

9.28.2016
Yu-Hsin’s paper on “Eyeriss: An Energy-Efficient Reconfigurable Accelerator for Deep Convolutional Neural Networks” has been accepted for publication in the Journal of Solid-State Circuits (JSSC) Special Issue on the 2016 International Solid State Circuits Conference (ISSCC)

9.20.2016
Prof. Sze to give a keynote at the NIPS 2016 Workshop on Efficient Methods for Deep Neural Networks (EMDNN)

8.25.2016
Prof. Sze to give an invited talk at the ICCAD 2016 Workshop on Hardware and Algorithms for Learning On-a-chip (HALO)

7.10.2016
We will be giving a tutorial on Hardware Architectures for Deep Neural Networks at MICRO-49

6.9.2016
Eyeriss featured in Microprocessor Report

5.9.2016
Prof. Sze to give a keynote at the CVPR 2016 Embedded Vision Workshop

4.20.2016
Prof. Sze to give an invited talk at the ICML 2016 Workshop on On-Device Intelligence

4.15.2016
Yu-Hsin to give a talk on Eyeriss at Deep Learning Summit 2016 in Boston

4.4.2016
Yu-Hsin to present a poster on Eyeriss at GTC 2016

4.1.2016
Amr and Zhengdong’s paper accepted to IEEE VLSI 2016

3.23.2016
Prof. Sze receives the Young Investigator Research Program (YIP) award from the Air Force Office of Scientific Research (AFOSR)

3.8.2016
Yu-Hsin Chen to present a paper at IEEE ISCA 2016

3.3.2016
Prof. Sze receives a 2016 3M Non-Tenured Faculty Award

2.12.2016
Eyeriss Project Page Online

2.3.2016
MIT News: Energy-friendly chip can perform powerful artificial-intelligence tasks

11.16.2015
Our deep learning chip (Eyeriss) is highlighted in an EETimes article about ISSCC 2016

11.5.2015
Amr Suleiman selected to present his work on low power object detection at the ISSCC 2016 Student Research Preview

10.14.2015
Amr’s paper on “An Energy-efficient Hardware Implementation of HOG-based Object Detection at 1080HD 60 fps with Multi-scale Support” has been accepted for publication in the Journal of Signal Processing Systems

10.12.2015
Yu-Hsin Chen to present a paper at IEEE ISSCC 2016

6.5.2015
Amr Suleiman awarded third place in the 2015 Broadcom Foundation University Research Competition

4.29.2015
Zhengdong Zhang to present a paper at IEEE ICIP 2015

4.21.2015
Amr Suleiman selected as a finalist in the 2015 Broadcom Foundation University Research Competition

4.16.2015
Yu-Hsin Chen receives the 2015 NVIDIA Graduate Fellowship

1.18.2015
Yu-Hsin Chen receives the 2015 Analog Devices Outstanding Student Designer Award

12.18.2014
Prof. Sze receives the 2014 DARPA Young Faculty Award (YFA)

10.6.2014
Yu-Hsin’s paper on “A Deeply Pipelined CABAC Decoder for HEVC Supporting Level 6.2 High-tier Applications” has been accepted for publication in IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)

9.22.2014
Mehul’s paper on “Energy and Area-Efficient Hardware Implementation of HEVC Inverse Transform and Dequantization” recognized as one of the “Top 10%” papers at IEEE ICIP 2014

9.1.2014
Prof. Sze’s co-edited book “High Efficiency Video Coding (HEVC) – Algorithms and Architectures” is published by Springer

8.1.2014
Prof. Sze will serve as a guest editor for the “Special Section on Efficient HEVC Implementations” in IEEE Transactions on Circuits and Systems for Video Technology

7.30.2014
Amr Suleiman to present a paper at IEEE SiPS 2014

5.21.2014
Yu-Hsin Chen and Mehul Tikekar to present papers at IEEE ICIP 2014

1.21.2014
Prof. Sze will chair a special session on “Efficient Design of HEVC Video-Codec Implementations” at IEEE ICIP 2014

12.19.2013
Prof. Sze will be giving a tutorial at IEEE ISCAS 2014 with Dr. Madhukar Budagavi on “Design and Implementation of Next Generation Video Coding Systems”

12.16.2013
Prof. Sze recipient of the 2013 Jonathan Allen Junior Faculty Award

10.18.2013
Sze, Vaikuntanathan named for career development professorships

9.23.2013
Heldt, Sze and Vaikuntananthan join EECS Faculty

2.20.2013
MIT News: MIT researchers build Quad HD TV chip

2.22.2011
EE Times: Algorithm paves path to better video