Engineering, Data, Machine learning

Mo He

*** ***** ***, *** **, Ithaca, NY *****

+1-607-***-**** ******@*******.***

EDUCATION

Electrical and Computer Engineering (ECE), Cornell University, Ithaca, NY, USA Aug 2017 – Expected Dec 2018 M.Eng. in ECE. GPA: 3.65

Courses enrolled: Computer Vision / Machine Learning and Pattern Recognition / Special Topics in ECE: Machine Learning in biomedical data / Database Management / OO Programming and Data Structure / Nonlinear Optimizations and Applications to ML and Power System Stability / Data Science for Engineers / Engr Probability & Stats II / Optimal Syst Analysis & Design School of Physics, Nankai University, China Sept 2013 – June 2017 B.S. in Physics, Poling Elite Class (awarded to 25 students out of 143 students) Major GPA: 89.5/100 (Overall GPA: 88/100) Rank: 8 out of 143 ECE-related Core Courses: Optoelectronic Imaging Technology / Microcomputer Principle and Application / Semiconductor Physics / Fundamental of Software Science and Computational Physics / Basis of Electronic Technology / Basis Experiment of Electronic Technology / Data Structures and Algorithms

EXPERIENCES I. Deep Learning

Face Recognition Tsinghua University, China Intern Jun 2018 – Aug 2018 Advisor: Dr. Changsong Liu, Associate Professor of EE department, Tsinghua University

• Contributed to cultivate appropriate image subsampling and resizing methodology in preprocessing for celebA and fer2013 dataset;

• Constructed Augmented-CNN model for multi-label prediction on gender, facial expression, etc.;

• Adjusted Neural Network structure and applied training techniques to generate over 97.4% accuracy on gender recognition. II. Physical and Mathematical Modeling

Study of conjugated organic materials University of Arizona, Arizona, USA J-1 Intern June 2015 – Aug 2015 Advisor: Professor Sumit Mazumdar, Professor and Dean of Physics Department, University of Arizona

• Developed a program in Mathematica (Linux ver.) based on semi-empirical Hȕckel Theory of molecular orbitals and quantum physics in modeling organic linear chains and did extensive linear algebra with the program;

• Calculated the charge density and bond order of Linear Chains for Ground State/Excited State with atom numbers up to 64, which provides insight into the metallic versus semi-conducting behavior in conjugated organic materials;

• Obtained a grade of A+ (97-100) for intern performance. PROJECT

I. Deep Learning

Deep learning in Financial Engineering Forecasting Cornell University, USA Cornell MEng Project Sept 2017 – May 2018 Advisor: Prof. Hsiao-Dong Chiang, Department of Engineering, Cornell University

• Contributed to utilizing various machine learning based models and optimization algorithms with the purpose of reaching maximum profits;

• Responsible for constructing Python LSTM model and MATLAB ANN model implementing Tier-1 search according to TRUST-TECH;

• Compared predictive performance of various local solver and optimizers respectively and composed comprehensive degree project report. II. Computer Vision

Automatic road extraction based on LiDAR dataset Cornell University, USA ECE 5470 Oct 2017 – Dec 2017 Advisor: Prof. Anthony Reeves, Department of Engineering, Cornell University

• Developed LiDAR data-preprocessing techniques in ArcGIS generating intensity & depth images;

• Responsible for marking the Ground Truth of actual roads’ region in VisionX annotation;

• Implemented proposed algorithms combining filtering and segmentation, etc., achieving over 0.65 accuracy at 40 locations in the US. III. Machine Learning

TADPOLE challenge: Alzheimer Disease Prediction Cornell University, USA ECE 5970 Sept 2017 – Dec 2017 Advisor: Prof. Mert Sabuncu, Department of Engineering, Cornell University

• Produced decent predictive result for baseline model and proposed multi-step RNN model for TADPOLE (The Alzheimer’s Disease Prediction Of Longitudinal Evolution);

• Contributed to proposed model improving, results analysis considering baseline method and proposed model, project presentation; Kaggle challenge: Robust digit recognition Cornell University, USA ECE 4950 Mar 2018 – May 2018 Advisor: Prof. Jayadev Acharya, Department of Engineering, Cornell University

• Created corrupted patterns during data preprocessing and constructed various neural network structures on twisted MNIST data;

• Applied tricks of tuning the parameter during network training and compared the performance of distinct algorithms;

• Utilized augmented CNNs in Keras using Tensorflow backend with 98.3% accuracy on test data, standing on 7/57 of private leaderboard. SKILLS Lab skills: Optical and Electronic Engineering lab skills Programming Languages: Java, Python 2.7/3.6 (Tensorflow / Keras), MATLAB, Mathematica, MySQL

Contact this candidate