Hon Wa Ng's repositories
Bayesian-Neural-Networks-and-Classification
This project implements probabilistic machine learning methods, including Bayesian classification, Gaussian discriminant models, and dropout in neural networks. It explores softmax regression, log-likelihood optimization, and performance evaluation using accuracy, ROC curves, and confusion matrices.
CISSP-Study-Guide
study material used for the 2018 CISSP exam
Data-Driven-Data-Science-Curriculum-Design
A data-driven approach to designing an optimal Data Science curriculum. This project extracts skills from job postings, applies NLP and clustering techniques (K-Means, Hierarchical, DBSCAN), and maps industry demands to educational recommendations. Uses Python, Scikit-learn, OpenAI embeddings, and Seaborn for visualization.
ML-Bias-Variance-Poisson-Regression
This repository contains implementations of advanced regression methods, including ordinary least squares, Poisson regression, and locally weighted regression. It also explores bias-variance decomposition for regularized mean estimators. The analysis is conducted on the Capital Bikesharing dataset using Python.
ML-Statistical-Methods-for-Classification-and-Approximation
This repository explores statistical and machine learning methods for classification and function approximation. It covers k-NN, Decision Trees, Information Theory, and Convexity, with Python implementations, theoretical explanations, model comparisons, and visualizations, making it a valuable resource for ML research and applications.
Ordinal-Logistic-Regression-Salary-Prediction
This repository contains an analysis of the Kaggle Machine Learning & Data Science Survey dataset, focusing on salary prediction using ordinal logistic regression and other classification models.
OSCP-Prep
A comprehensive guide/material for anyone looking to get into infosec or take the OSCP exam
Salary_Analysis_StackOverflow
Statistical analysis of salary differences based on job mode (remote vs. in-person) and education levels using Welch’s t-test, ANOVA, and bootstrapping.
Speech-Disorder-Classification-ML
This repository contains a machine learning-based classification system for detecting speech disorders from acoustic and spectrogram features. It includes data preprocessing, feature extraction, and various classification models such as logistic regression, SVM, random forest, and CNNs.