羅紹瑄  Jeff Lo

I am interested in building codes related to  Machine/Deep Learning, Computer Vision, Mobile/Web applications, and Linux kernel. Besides, I enjoy studying state-of-the-art research and implementing algorithms from scratch.

    

Education



2020 - 2022

National Cheng Kung University

Master of Electrical Engineering (Program of Computer Science)
Ce-Kuen Shieh's lab
Focus on Parallel/Distributed Systems




2016 - 2020

National Sun Yat-sen University

Bachelor of Computer Science Engineering


Work Experience

Software Engineer Intern

HP

July 2021 - September 2021
Taipei, Taiwan

Develop two programs from scratch in 10 weeks including:
1. Big Data collection tool (C++)
        ◾ collect 80000+ device information in 5 seconds

2. Production information prediction system  (Python)
        ◾ leverage state-of-the-art Machine Learning algorithms 
        ◾ Database connection


Award/Experience

Microsoft FLAML Contributor
(Open Source Project)

A fast and lightweight autoML library developed by Microsoft Research

Kaggle Competition Top 0.1%

Predict Future Sales
Rank: 20/12544
A regression task in structured data


2020 AICUP Top 7%

Medical data De-identification
Rank: 36/531
A Name Entity Recognition task in medical conversation data

Collegiate Programming Examination Top 5%

Date: 2018/05/29
Problems solved: 4/7
Rank: 110/2181

Skills

Programming Languages

Python
C/C++
Java
C#
R

Machine/Deep Learning

Neural Network
Transfer Learning
Ensemble Learning
Self-Training

Computer Vision


Image Process
Image Classification
Object Detection
Object Tracking

Application


Android Application
ASP.NET
Socket Programming

    Hadoop      Docker      OpenCV      tensorflow      Scikit-Learn      Windows API      Ubuntu      git     


Projects

Waymo dataset object detection/tracking

        ◾ Object Detection: fine tune pretrained models                     from tensorflow zoo include SSD ResNet and                      CenterNet HourGlass architectures.
        ◾ Object Tracking: Implement a custom object                       tracking API including features like deepsort and               non-maximum suppression.

    Vehicle data analytics Android application

              ◾ Real-time data display
              ◾ Real-time outlier detection
              ◾ User Database

   

Image Process/Classification

     ◾ Implement image process algorithms from scratch
     ◾ leverage OpenCV API in image/video process
     ◾ Train high accuracy models over 7+ image datasets
     ◾ Strong knowledge in Transfer learning and Neural              Network training details
                 

     Socket Programming

              ◾ Multi-user chat room
              ◾ Unzip file server (Huffman Coding)
              ◾ TCP congestion control simulation