Welcome to my GitHub page!
My name is Titus and I'm a data scientist from Singapore
🏫 I’ve a Masters degree in Artificial Intelligence 👨🎓 but I'm forever playing catch-up with the rapidly developing field of data science 🤣. Nonetheless, those nights spent learning the fundamentals of AI (computer vision, natural language processing, recommender systems, machine learning, machine learning engineering, etc) were very memorable!
👨🏻💻 This year, I've been dabbling in plenty of LLM application development. I enjoy building agents and agentic RAG systems and basically live on the Llamaindex and Langchain documentation page!
🌱 I’m currently learning more about full stack development to become a more complete developer - coding is so fun 👨💻! 
🚀 Check out my personal webpage!
| 🎁 Projects | 📝 Summary | ⭐ Domains | 🛠️ Tools |
| You Only Edit Once | Using object detection models to trim and beautify diving videos - feel free to try it out! |  |
 |
| A Song for Singapore | Using LSTM, GRU, Seq2Seq models and GPT-2 to write lyrics, melody, harmony and sing out Singapore's next national day song! |  |
|
| The Coffee Recommender System | Using deep learning and collaborative filtering to develop Singapore's coffee recommendation system. |
 |
 |
| AI Backdoor Catcher | Using neural cleansing, neural attention distillation and other advanced methods to identify backdoors embedded in AI models |
 |
|
| Face Mask Classification | This was an attempt at developing and quantizing image classification models for deployment to edge device through GCP to support the government's COVID-19 face mask detection enforcement measures. |
 |
|
| Skimlit | The aim of this project is to make chunky abstracts/summaries appear skimmable,and follows the experiments (and data) by the paper: [PubMed 200k RCT: a Dataset for Sequenctial Sentence Classification in Medical Abstracts](https://arxiv.org/abs/1710.06071). |
|
|
| FoodVision-Tensorflow | This project is a personal project to develop a computer vision classification model for food images. |
|
|
| Improving NYC 311 Efficiency | Forecasting closure duration of 311 complaints to support NYC agencies in case prioritization |  |
 |
| The IoT Liquid Pipeline Monitoring System | Developing an entire proof-of-concept for IoT-driven pipelines using Arduino, SQL and Python. |  |
|