jayenliao Goto Github PK

followers: 9.0 following: 33.0 repos: 27.0 gists: 0.0

Name: Jay Liao

Type: User

Bio: Passionate data scientist interested in using DS, especially machine learning with graphs, to explore different issues.

Location: Taipei, Taiwan

Blog: https://www.linkedin.com/in/jc-liao/

廖傑恩 Jay Chiehen Liao

Jay Liao's Projects

academic-kickstart

📝 Easily create a beautiful website using Academic, Hugo, and Netlify

This is the first mid-term project of Statisical Consulting, a course at Department of Statistics and Institue of Data Science, National Cheng Kung University, Taiwan. In this project, we followed Heiberger and Holland (2015) to demonstrate a complete analysis of covariance (ANCOVA) on the dataset hotdog.

data-management-rshiny-tutorial

This is a tutorial presentation for Data Management, a course in National Cheng Kung University, Taiwan. We demonstrate how instructors can use R shiny to teach fundamental Statistics and basic R techniques, such as data wrangling and data visualization.

dl-aoi

This is assignment 5 of Deep Learning, a course at Institute of Data Science, National Cheng Kung University. This project aims to utilize deep learning techniques to perform defect classification for AOI images.

dl-computational-graph

This is assignment 2 of Deep Learning, a course at Institute of Data Science, National Cheng Kung University. This project aims to extract features from images and to construct models to perform image classification.

dl-esun-public

此為Deep Learning期末專題公開版（因競賽資料不可公開）。本組參加「TBrain AI實戰吧」競賽平上的「玉山人工智慧挑戰賽2021夏季賽」，進行中文手寫影像辨識的任務，並將訓練好的模型部署在RESTful API Server上。比賽目標是預測包含一個文字的影響資料判別，目標類別共801類，分別為800字與1類isnull。

dl-image-classification

This is an assignment project of Deep Learning, a course at Institute of Data Science, National Cheng Kung University. This project aims to extract features from images and to construct models to perform image classification.

dl-lenet

This is assignment 4 of Deep Learning, a course at Institute of Data Science, National Cheng Kung University. This project aims to construct LeNet-related models to perform image classification.

dl-lenet-numpy

This is assignment 3 of Deep Learning, a course at Institute of Data Science, National Cheng Kung University. This project aims to construct LeNet-related models to perform image classification.

dl-object-detection

This is assignment 6 of Deep Learning, a course at Institute of Data Science, National Cheng Kung University. This project aims to utilize deep learning techniques to perform object detection. We implement with PyTorch.

dl-semantic-segmentation

This is assignment 7 of Deep Learning, National Cheng Kung University. This project demonstrates the work of participating in Woodscape Semantic Segmentation Challenge 2021, a competition on CodaLab with the user name jay.chiehen. We utilized techniques of computer vision and image processing to perform semantic segmentation for autonomous driving.

drbc

This is the tensorflow implementation for CIKM'19 DrBC: A novel graph neural network approach to identify high BC nodes

early-stopping-pytorch

Early stopping for PyTorch

g0v-twly-voter-guide-android

g0v taiwan legislative yuan voter guide android project

get-book-info

This is a small side project. The objective is to get the basic information of the book based on the given ISBN.

intro-dl

A small tutorial of introduction deep learning

introduction_graph_tool

Introduction to Python's Graph-Tool

jayenliao

Config files for my GitHub profile.

kaohsiung-vote-2018-2020

This is a final project presentation for Data Management, a course in National Cheng Kung University, Taiwan. In brief, we analyzed three votes in Kaohsiung in 2018-2020.

nfl-speed-prediction

This is the final project of Time Series Analysis, a course at the programme of Data and Business Analytics at Rennes School of Business, France. This study aims to use two types of method to predict NFL players' speed during each play in games, including ARIMA and LSTM.

optimization-cs-ba-fpa

This project aimed to implement three well-known meta-heuristic algorithms: cuckoo search (CS), bat algorithm (BA), and flower pollination algorithm (FPA). We found that three algorithms could have a promising performance generally. It might need more runs to be converged when training BA. The time cost of BA was the highest while the differences of time cost among three algorithms were not so large, which might not matter when the number of training runs was not large. We also tuned λ in CS and FPA with the findings of the weakness of larger λ values. A demo video of training process is available on YouTube: https://youtu.be/hlKvODBUyeI.

optimization-de-pso-fa

This project aimed to implement three well-known meta-heuristic algorithms: differential evolution (DE), particle swarm optimization (PSO), and firefly algorithm (FA). We set up the numerical experiments to compare 3 algorithms with different numbers of points.

optimization-l1-regularization

This is a mid-term project of Optimization Methods, a course of Institute of Data Science, National Cheng Kung University. This project aimed to construct the linear regression with L1 regularization and the logistic regression with L1 regularization.

jayenliao Goto Github PK

廖傑恩 Jay Chiehen Liao

Jay Liao's Projects

Recommend Projects

Recommend Topics

Recommend Org