kwokhing Goto Github PK

ai-planet-llm-bootcamp-challenge

A LLM challenge to (i) fine-tune pre-trained HuggingFace transformer model to build a Code Generation language model, and (ii) build a retrieval-augmented generation (RAG) application using LangChain

creating-a-multi-sports-event-dashboard-in-powerbi

A demonstration on creating a simple multi-sports event dashboard using PowerBI and DAX

demo-on-automated-fact-checking-using-s-bert

In this demo, we illustrate the the possibility of using Semantic Search + Recognising Textual Entailment with Gradio to build an automated fact checking tool

exploratory-data-analysis-on-smrt-tweets

Demo on performing exploratory data analysis (EDA) on train service disruptions based on scrapped (user generated contents) tweets from the train operator's (SMRT) twitter account

gsp345-automating-infrastructure-on-google-cloud-with-terraform-challenge-lab

Steps to complete the Automating Infrastructure on Google Cloud with Terraform: Challenge Lab (GSP345)

kwokhing

models

Models and examples built with TensorFlow

network-analysis-on-mrt-station

Demo on applying the concept of network analysis on a network of connected railway stations, attempting to identify the important stations (nodes) in this network. Web scraping techniques using rvest package is also briefly discussed upon.

pencils-of-promise

Data for A Cause - Pencils of Promise

regression-with-a-crab-age-dataset

A light-weight Kaggle challenge to predict crabs' age

rfacebook-demo

Demo on using the Rfacebook package to scrape/mine user generated contents (UGCs) from public FB pages. Simple sentiment, text, trend and posting frequency analysis are performed on these scraped UGCs

sentimentanalysis-python-demo

Submission of an in-class NLP sentiment analysis competition held at Microsoft AI Singapore group. This submission entry explores the performance of both lexicon & machine-learning based models

shap-xai-demo

Demo on performing Explainable AI using the SHAP Library

tf2-cifar10-cnn-demo

Demo on performing multiclass image classification using Convolutional Neural Network (CNN) in Tensorflow 2. Techniques such as earlystopping, batchnormalizing and dropout are explored to prevent overfitting

the-best-things-in-life-are-free

A Repository of Learning Resources & Massive Open Online Courses (MOOCs) for personal development

udacity-bertelsmann-intro-to-ml-with-tensorflow

Udacity x Bertelsmann Scholarship - Introduction to Machine Learning with TensorFlow

udacity-project-dog-classification

This project from the Udacity Deep Learning Nanodegree Programme deploys the use of Convolutional Neural Networks (CNN) in PyTorch to classify dog breeds.

uplimit-project-podcast-frontend

A LLM app to summarize a podcast episode, identifies podcast guests and attempts to retrieve the guest's public information from wikipedia, and identifies key highlights using OpenAI ChatGPT with prompting techniques

visualizing-datasets-with-facets

Demo on using Facets: An Open Source Visualization Tool for Machine Learning Training Data developed by Google's PAIR Initiative

wids-datathon-patient-survival

A challenge to create a model that uses data from the first 24 hours of intensive care to predict patient survival

yandexcatboost-python-demo

Demo on the capability of Yandex CatBoost gradient boosting classifier on a fictitious IBM HR dataset obtained from Kaggle. Data exploration, cleaning, preprocessing and model tuning are performed on the dataset