About ML and AI
​
Gain a comprehensive understanding of developing, deploying, and integrating machine learning models into user applications. This curriculum covers the entire lifecycle from data preparation to deployment and integration.
ML/AI Career Outcomes
​
Introduction to ML, types and workflow
​
Exploratory Data Analysis and Feature selection
​
Model development, training, and evaluation
​
Model deployment, serving, and Containerising
​
Evaluating model metrics
Program Outline
Module 1: Fundamentals of ML and Data Preparation
Introduction and types of ML applications
​
Preparing Python environment (NumPy, pandas, scikit-learn)
​
Data collection, preprocessing, and exploratory data analysis
​
Data visualisation
Feature engineering and selection
Module 2: Model Training and Evaluation
Common ML algorithms, and suitability of models for each use case
​
Splitting data into training and testing datasets and training with scikit-learn
​
Evaluate models using metric classification or Cross-validation techniques
​
Hyperparameter tunning - overfitting and underfitting
Module 3: Model Deployment and Serving
Model serialization (saving and loading using pickle, job lib, and ONNX)
​
Using Flask to create APIs for model inference
​
Deploy Flask application to a cloud platform
​
Containerise using Docker
Module 4: Integrate ML models into user applications
Basic frontend and mobile integration
​
Monitoring and maintaining models in Production
​
Setup a basic model update process