👋 Hello, I'm Kenneth Leung
Thanks for popping by! As an avid learner, bold builder, curious explorer, and driven doer, I enjoy seeking and solving meaningful problems with data and tech.
Join me on a journey of AI discovery! Follow me on GitHub , Medium , and LinkedIn to stay updated with engaging and practical content.
You can find my tech portfolio here (which I started building before the age of LLMs), where every project is borne out of curiosity and inspiration.
Looking for career guidance/mentorship, tech discussions, brainstorming, or potential referrals? Feel free to reach out
If you’ve found my projects, articles, or resources helpful, you can support my work here:
Computer Vision Database Management Data Extraction and Web Scraping Data Science Certification Guides Data Science Toolkit Data Science in the Real World Generative AI and Agentic AI Insights from Data Science Talks Machine Learning MLOps Natural Language Processing Networks and Graphs Responsible AI Sports Analytics Visualization Web Development Web3 and Metaverse Writing for DataCamp Writing Tips
Projects with ⭐ are my personal favourites, so do check them out!
Title
Article
Repo
Classifying Images of Alcoholic Beverages with fast.ai v2
🔗 🔗
Russian Car Plate Detection with OpenCV and TesseractOCR
🔗 🔗
Evaluate OCR Output Quality with Character Error Rate (CER) and Word Error Rate (WER)
🔗 🔗
Top Python libraries for Image Augmentation in Computer Vision
🔗 🔗
⭐ PyTorch Ignite Tutorial - Classifying Tiny ImageNet with EfficientNet
🔗 🔗
Practical Guide to Transfer Learning in TensorFlow for Multiclass Image Classification
🔗 🔗
Title
Article
Repo
⭐ Definitive Guide to Creating a SQL Database on Cloud with AWS and Python
🔗 🔗
PyMySQL - Connecting Python and SQL for Data Science
🔗 🔗
Data Extraction and Web Scraping 🧰
Title
Article
Repo
Using OneMap API to extract Singapore postal codes, coordinates and travel distance
-
🔗
A Detailed Web Scraping Walkthrough Using Python and Selenium
🔗 🔗
⭐ How to Web Scrape Wikipedia using LangChain Agents and Tools with OpenAI's LLMs and Function Calling
🔗 🔗
Data Science Certification Guides 👨🎓
Title
Article
Repo
3 Steps to Get AWS Cloud Practitioner Certified in 2 Weeks
🔗 🔗
3 Steps to Get Tableau Desktop Certified in 2 Weeks
🔗 -
⭐ No-Frills Guide to Passing the AWS Certified Machine Learning Specialty Exam
🔗 -
Microsoft Certified: Azure AI Engineer Associate - Study Notes
-
🔗
Title
Article
Repo
Common Python codes for Data Wrangling
-
🔗
Enhance your Python code’s readability with pycodestyle
🔗 -
Free Resources for Generating Realistic Fake Data
🔗 -
Most Starred and Forked GitHub Repos for Data Science and Python
🔗 -
Most Starred and Forked GitHub Repos for Data Science and R
🔗 -
Automatically Generate Machine Learning Code with Just a Few Clicks
🔗 -
Read and Modify Image Metadata with Python
🔗 🔗
Top Tips to Google Search Like a Seasoned Data Scientist
🔗 -
How to Swap Day and Month of Incorrectly Formatted Excel Dates
🔗 -
Data Science in the Real World 🌏
Title
Article
Repo
Exploring Illegal Drugs in Singapore — A Data Perspective
🔗 🔗
Pharmacokinetic Modeling of Drug Concentration Trajectories using Ordinary Differential Equations (ODE) and Global Optimization with Differential Evolution
-
🔗
Healthcare’s AI Future — In Conversation with Andrew Ng and Fei-Fei Li
🔗 -
Real-World Data Science Use Cases in the Insurance Industry
🔗 -
⭐ Failed-ML: Compilation of high-profile real-world examples of failed machine learning projects
🔗 🔗
Generative AI and Agentic AI 🤖
Title
Article
Repo
Generative AI Pharmacist - Macy
🔗 🔗
AI Generated Patient Information Videos for Partial Nephrectomy with Expert Validation – A Pilot Study
🔗 🔗
⭐ ChatPod - Q&A over your Podcasts with Whisper, FAISS, and LangChain
🔗 🔗
⭐ Running Llama 2 and other Open-Source LLMs on CPU Inference Locally for Document Q&A
🔗 🔗
⭐ Finance-LLMs - Comprehensive Compilation of Real-World LLM Implementation in Financial Services
🔗 🔗
⭐ Text-to-Audio Generation with Bark, Clearly Explained
🔗 🔗
Guide to ChatGPT's Advanced Settings — Top P, Frequency Penalties, Temperature, and More
🔗 -
Inside the Leaked System Prompts of GPT-4, Gemini 1.5, Claude 3, and More
🔗 -
⭐ Exposing Jailbreak Vulnerabilities in LLM Applications with ARTKIT
🔗 🔗
How to Benchmark DeepSeek-R1 Distilled Models on GPQA Using Ollama and OpenAI's simple-evals
🔗 🔗
Using Google’s LangExtract and Gemma for Structured Data Extraction
🔗 🔗
⭐ How Agent Handoffs Work in Multi-Agent Systems
🔗 🔗
How Agents Plan Tasks with To-Do Lists
🔗 🔗
How Cursor Actually Indexes Your Codebase
🔗 -
Building Human-In-The-Loop Agentic Workflows
🔗 🔗
⭐ Claude-Music: Stream great music in your Claude Code sessions, with an AI DJ that matches your vibes
-
🔗
Insights from Data Science Talks 👨🏫
Title
Article
Repo
Bridging AI’s Proof-of-Concept to Production Gap — Insights from Andrew Ng
🔗 -
Title
Article
Repo
Exploring Condominium Rental Prices with Web Scraping and Exploratory Data Analysis
🔗 🔗
Using Ensemble Regressors to Predict Condominium Rental Prices
🔗 🔗
The Dying ReLU Problem, Clearly Explained
🔗 -
Why Bootstrapping Actually Works
🔗 -
⭐ Assumptions of Logistic Regression, Clearly Explained
🔗 🔗
Data-Centric AI Competition - Tips and Tricks of a Top 5% Finish
🔗 🔗
Credit Card Fraud Detection with AutoXGB
🔗 🔗
⭐ Micro, Macro & Weighted Averages of F1 Score, Clearly Explained
🔗 -
Principal Component Regression - Clearly Explained and Implemented
🔗 🔗
⭐ Feature Selection with Simulated Annealing in Python, Clearly Explained
🔗 🔗
Quick Primer on Types of Missing Data and Imputation Techniques
🔗 -
Imputation of Missing Data in Tables with DataWig
🔗 🔗
MLOps - Machine Learning Operations 👨🔧
Title
Article
Repo
Key Learning Points from MLOps Specialization — Course 1/4
🔗 🔗
Key Learning Points from MLOps Specialization — Course 2/4
🔗 🔗
Key Learning Points from MLOps Specialization — Course 3/4
🔗 🔗
Key Learning Points from MLOps Specialization — Course 4/4
🔗 🔗
⭐ End-to-End AutoML Pipeline with H2O AutoML, MLflow, FastAPI, and Streamlit for Insurance Cross-Sell
🔗 🔗
How to Dockerize Machine Learning Applications Built with H2O, MLflow, FastAPI, and Streamlit
🔗 🔗
⭐ Building and Managing an Isolation Forest Anomaly Detection Pipeline with Kedro
🔗 🔗
⭐ Scaling Feature Engineering Pipelines with Feast and Ray
🔗 🔗
Natural Language Processing 📑
Title
Article
Repo
COVID-19 Vaccine — What’s the Public Sentiment?
🔗 🔗
Keyword Extraction and Analysis Pipeline with KeyBERT and Taipy
🔗 🔗
Title
Article
Repo
⭐ Network Analysis and Visualization of Drug-Drug Interactions
🔗 🔗
How to Deploy Interactive Pyvis Network Graphs on Streamlit
🔗 🔗
A No-Code Approach to Building Knowledge Graphs
🔗 🔗
⭐ Text-to-SQL with GraphRAG on Neo4j Knowledge Graph Semantic Representation of SQL Databases
Coming Soon 🔗
Title
Article
Repo
Responsible AI Masterclass (for Institute of Banking and Finance Singapore)
🔗 🔗
Title
Article
Repo
⭐ Analyzing English Premier League VAR Football Decisions
🔗 🔗
Combining Python and R for FIFA Football World Ranking Analysis
🔗 🔗
Title
Article
Repo
Uniform Singapore Energy Price and Demand Forecast Dashboard (with Plotly Dash)
-
🔗
Visualizing Fortune 500 Companies in a Bar Chart Race
🔗 🔗
How to Easily Draw Neural Network Architecture Diagrams
🔗 🔗
Title
Article
Repo
⭐ Post COVID-19 Vaccination Wait-Time Tracker (with Python Flask)
🔗 🔗
From HTTP to HTTPS — Easily Secure Flask Web Apps With Talisman
🔗 -
⭐ Food King Directory (in collaboration with Night Owl Cinematics)
🔗 🔗
Title
Article
Repo
The Web3 / Metaverse Glossary — A Keyword Guide to the Tech Future
🔗 -
Title
Article
Repo
⭐ What Mature Data Infrastructure Looks Like
🔗 -
Democratizing Data in Government Agencies
🔗 -
A Survey Into Data Governance Tools
🔗 -
Scaling Data Science With Data Governance
🔗 -
3 Reasons Why All Teams Should Learn SQL
🔗 -
3 Reasons Why All Teams Should Learn R
🔗 -
How Tableau Helps Your Organization Achieve Greater Data Insights
🔗 -
How PowerBI Helps Your Organization Achieve Greater Data Insights
🔗 -
Title
Article
Repo
Create a Clickable Table of Contents for Your Medium Posts
🔗 -