Programme Curriculum

Module 1: Core Python Programming Essentials

Topics Covered

• Getting started with Python and environment setup

• Program logic: conditions, loops, and flow control

• Writing reusable code using functions and modules

• Working with Python data collections (lists, tuples, sets, dictionaries)

• Object-Oriented Programming concepts and implementation

• Exception handling and debugging practices

• Overview of essential libraries: NumPy, Pandas, Matplotlib

• Data analysis, scientific computation, and visualisation

• Practical scripting applications (file handling, automation, web scraping)

• Hands-on projects: Python Web Scraper, Automated Data Cleaning Tool

Learning Outcomes

• Write efficient Python programs to solve real-world problems

• Master core programming concepts including OOP and modular coding

• Handle and manipulate complex data structures with confidence

• Use popular Python libraries for data analysis and visual representation

• Identify, debug, and handle runtime errors effectively

• Build automation scripts for data extraction and processing

• Complete practical mini-projects to reinforce learning

Module 2: Preparing and Optimising Data for Machine Learning

Topics Covered

• Cleaning and refining raw datasets

• Scaling techniques: normalisation and standardisation

• Feature selection and transformation

• Dimensionality reduction methods

• Encoding categorical data

• Advanced feature engineering strategies

• Handling class imbalance in datasets

• SQL fundamentals for dataset extraction and analysis

Learning Outcomes

• Prepare raw data for machine learning workflows

• Apply scaling and transformation techniques for consistent input

• Reduce noise and complexity using dimensionality reduction

• Create meaningful features to improve model performance

• Manage imbalanced datasets for fairer model outcomes

• Use SQL to query, filter, and combine data from relational databases

Module 3: Practical Machine Learning with Real Examples

Topics Covered

• Supervised learning: regression and classification models

• Algorithms: Decision Trees, KNN, Naive Bayes, SVM

• Ensemble techniques: Random Forest, Gradient Boosting

• Unsupervised learning: K-Means, DBSCAN clustering

• Model evaluation and validation techniques

• Cross-validation and hyperparameter optimisation

• Advanced boosting methods: XGBoost, LightGBM

• Model stacking and blending strategies

• Capstone mini-project: Credit Risk Prediction System

Learning Outcomes

• Build and deploy regression and classification models

• Apply popular machine learning algorithms confidently

• Use ensemble and boosting techniques for higher accuracy

• Evaluate models using industry-standard metrics

• Fine-tune models using hyperparameter optimisation

• Combine multiple models for performance improvement

• Implement ML concepts through a real-world project

Module 4: Deep Learning and Neural Networks

Topics Covered

• Fundamentals of neural networks and deep learning

• Training strategies and optimisation techniques

• Convolutional Neural Networks (CNNs) for computer vision

• Recurrent Neural Networks (RNNs) for sequential data

• Transfer learning with pre-trained models (ResNet, BERT, Transformers)

• Hands-on deep learning with TensorFlow/Keras using Google Colab

Learning Outcomes

• Understand deep learning architecture and training workflows

• Build CNN-based image recognition systems

• Create RNN-based models for time-series and text data

• Apply transfer learning for faster, high-performance model development

• Train and evaluate deep learning models using modern frameworks

• Gain practical experience building scalable DL applications

Module 5: Industry-Focused AI Applications

Computer Vision with OpenCV

• Image enhancement and processing

• Face recognition and detection

• Shape and contour detection

• Object tracking and motion analysis

• Real-time video processing applications

Natural Language Processing & Generative AI

• Large Language Models and generative AI foundations

• Prompt engineering techniques

• Using OpenAI APIs for AI-powered apps

• Building Q&A systems with LLMs

• LangChain framework and DSPy integration

Applied AI Projects

• AI applications in healthcare

• Time-series forecasting systems

• Recommendation engines for e-commerce

Learning Outcomes

• Implement computer vision solutions using OpenCV

• Build NLP and generative AI applications using LLMs

• Design intelligent systems using LangChain and DSPy

• Develop domain-specific AI solutions across industries

• Gain hands-on experience with real-world, production-style projects

Module 6: Model Deployment, MLOps & Advanced Topics

Topics Covered

• End-to-end machine learning deployment workflow

• Containerisation using Docker

• Building APIs with Flask and FastAPI

• Cloud deployment on AWS, GCP, and Azure

• Model monitoring, versioning, and maintenance

• CI/CD pipelines for ML systems

• MLOps best practices and lifecycle management

• Fault detection and performance diagnostics

• Model tracking using MLflow or Weights & Biases

• Live deployment demo (Streamlit frontend + backend API)

Learning Outcomes

• Deploy machine learning models to production environments

• Containerise applications for scalable and portable deployment

• Expose ML models as APIs using industry frameworks

• Implement cloud-based deployment strategies

• Monitor, update, and manage models post-deployment

• Apply MLOps principles for reliable ML systems

• Build and deploy full-stack AI applications with Streamlit and APIs