Hao Zhang

The Robotics Institute
School of Computer Science
Carnegie Mellon University
Pittsburgh, PA 15213, USA

Email: hao AT cs.cmu.edu

[Google Scholar][Petuum]



I am currently a graduate student in the Robotics Institute, Carnegie Mellon University. My advisor is Prof. Eric Xing.
I received the M.S. degree from Computer Science and Engineer Department in Shanghai Jiao Tong University in 2014, under the supervision of Prof. Liqing Zhang. Before that, I completed my Bachelor's degree from 2008 to 2011 at South China University of Technology, majoring in Computer Science.

Research Interest

My research interest is in the intersection area of machine learning, distributed system and computer vision.

Work Experience


Projects & Publications

Machine Learning

Poseidon: A System Architecture for Efficient GPU-based Deep Learning on Multiple Machines
H.Zhang, Z.Hu, J.Wei, P.Xie, G.Kim, Q.Ho, E.P.Xing
[arXiv] [paper] [project] [wiki] [on Petuum] [bib]

Learning Concept Taxonomies from Multi-modal Data
H.Zhang, Z.Hu, Y.Deng, M.Sachan, Z.Yan, E.P.Xing
ACL 2016 (To appear)
[arXiv] [paper] [supplement] [bib]

Combining the Best of Convolutional Layers and Recurrent Layers: A Hybrid Network for Semantic Segmentation
Z.Yan, H.Zhang, Y.Jia, T.Breuel, Y.Yu
[arXiv] [paper] [project page] [code (available upon request)] [bib]

GeePS: Scalable Deep Learning on Distributed GPUs with a GPU-specialized Parameter Server
H.Cui, H.Zhang, G.R.Ganger, P.B.Gibbons, E.P.Xing
EuroSys 2016
[paper] [code] [bib]

Automatic Photo Adjustment Using Deep Learning
Z.Yan, H.Zhang, B.Wang, S.Paris, Y.Yu
TOG 2016
ICCP 2016 (Invited Poster)
[paper] [project page] [supplement] [code&datasets] [ICCP Poster] [bib]

On the Reducibility of Submodular Functions
J.Mei, H.Zhang, B.Lu
[paper] [supplement] [poster] [bib]

HD-CNN: Hierarchical Deep Convolutional Neural Network for Large Scale Visual Recognition
Z.Yan, H.Zhang, R.Piramuthu, V.Jagadeesh, D.DeCoste, W.Di, Y.Yu
ICCV 2015
[paper] [project page] [supplement] [code] [poster] [video] [bib]

Dynamic Topic Modeling for Monitoring Market Competition from Online Text and Image Data
H.Zhang, G.Kim, E.P.Xing
KDD 2015
[paper] [project page] [slides] [poster] [bib]

Brain Computer Interface

A Boosting-based Spatial-Spectral Model for Stroke Patients’ EEG Analysis in Rehabilitation Training
Y.Liu, H.Zhang, L.Zhang
IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2015
[paper] [bib]

Common Spatial-Spectral Boosting Pattern for Brain-Computer Interface
Y.Liu*, H.Zhang*, L.Zhang
(* indicates equal contribution)
ECAI 2014
[paper] [bib]

Gaussian Mixture Modeling in Stroke Patients’ Rehabilitation EEG Data Analysis
H.Zhang, Y.Liu, J.Liang, J.Cao, L.Zhang
EMBC 2013
[paper] [bib]

A Tensor-Based Scheme for Stroke Patients' Motor Imagery EEG Analysis in BCI-FES Rehabilitation Training
Y.Liu, M.Li, H.Zhang, H.Wang, J.Li, J.Jia, Y.Wu, L.Zhang
Journal of Neuroscience Methods, 2013
[paper] [bib]

Single-Trial Discrimination of EEG Signals for Stroke Patients: A General Multi-Way Analysis
Y.Liu, M.Li, H.Zhang, J.Li, J.Jia, Y.Wu, J.Cao, L.Zhang
EMBC 2013
[paper] [bib]



Professional Activities

Honors & Awards

ICML Travel Grant, 2016
KDD Travel Grant, 2015
Excellent Graduates (top 5%), SJTU, 2014
Google Excellent Scholarship (National wide), Google Inc., 2013
Scholarship for Graduates, SJTU, 2011-2014
Early Graduation Honor (top 1%) in SCUT, 2011
The Elite Class of Computer Science (About 40 best students out of 1500 freshmen are chosen), 2008-2011
First-class Student Scholarship in SCUT, 2008-2011