This repository showcases my practical assignments and projects which demonstrated my ability to apply machine learning, data analysis, and AI problem-solving techniques to real-world scenarios using Python.
-
Mini AI Application Examples
Implementations of classic AI problems using Python and Google Colab.
Includes:- Search problem (Warehouse Robot Path Planning)
- Regression problem (Predictive Modeling)
- Classification problem (Multi-Class Text or Image Classification)
- Evaluation, comparison, and reflection of AI techniques
-
AI Reasoning & Knowledge Representation Notes
Study notebooks covering topics such as:- Logic representation
- Bayesian networks
- Markov Decision Processes (MDPs)
- Reinforcement Learning
-
Assignment 2 – Data Exploration & Preparation
Comprehensive exploratory data analysis (EDA) and preprocessing on a real-world dataset.
Techniques include:- Data cleaning, normalization, binning
- Visualization (boxplots, scatterplots, heatmaps)
- Outlier detection and correlation analysis
-
Assignment 3 – Classification Project
End-to-end machine learning workflow for predicting customer satisfaction.
Models used:- Logistic Regression, SVM, Random Forest, KNN, Decision Tree, XGBoost
Includes feature engineering, model tuning, and explainability (using SHAP/LIME).
- Logistic Regression, SVM, Random Forest, KNN, Decision Tree, XGBoost
- Python, pandas, NumPy, scikit-learn, matplotlib, seaborn
- H2O AutoML, SHAP, LIME, Google Colab
- Jupyter Notebook for reproducible documentation
- Applied CRISP-DM methodology to structure analytics workflows
- Developed explainable and interpretable ML models
- Strengthened understanding of AI search, regression, and classification
- Built reproducible ML pipelines and professional reports
Yuanshuo Gou
Master of Artificial Intelligence
University of Technology Sydney