About This Course
This AI & Machine Learning Course is designed to help you understand how computers learn from data. You start with Python, mathematics and statistics for ML, and gradually move into core algorithms like regression, classification, clustering and basic deep learning.
Through hands‑on labs and projects, you will work with real‑world datasets, train and evaluate models, and present your results clearly. By the end of the course, you’ll be comfortable implementing ML workflows and prepared for entry‑level AI / ML, data science or advanced analytics roles, or for further specialised study.
Syllabus Overview
Module 1
Python, Maths & ML Foundations
- Introduction to AI & ML – terminology, applications & workflow
- Python for Data Science – NumPy, pandas, Matplotlib / Seaborn
- Mathematics for ML – linear algebra & calculus (conceptual focus)
- Statistics & Probability for ML – distributions, estimation, tests
- Data Pre‑processing – cleaning, encoding, scaling & train‑test splits
- Lab: Exploratory Data Analysis (EDA) on a real‑world dataset
Module 2
Supervised & Unsupervised Learning
- Regression Algorithms – Linear, Polynomial, Regularised models
- Classification Algorithms – Logistic Regression, k‑NN, SVM, Trees
- Model Evaluation – accuracy, precision/recall, ROC‑AUC, cross‑validation
- Ensemble Methods – Random Forests, Gradient Boosting (intro)
- Unsupervised Learning – k‑Means, Hierarchical Clustering, PCA
- Lab: Build & compare ML models on structured datasets
Module 3
Deep Learning Basics, Deployment & Projects
- Neural Network Fundamentals – perceptron, activation functions, loss
- Deep Learning with Keras / TensorFlow (intro) – building simple models
- Working with Image / Text Data (conceptual & basic hands‑on)
- Model Optimisation – tuning, regularisation, avoiding overfitting
- Intro to Model Deployment – saving, loading and using models in apps
- Lab: End‑to‑end ML / DL mini‑project with presentation
*Exact modules and tools may vary as per institution and curriculum.
Projects
Hands‑on Assignments & Capstones
- Regular lab‑based assignments in Python, EDA and model building
- Mini‑projects: prediction, classification & clustering case studies
- Domain‑based projects (e.g. finance, marketing, healthcare datasets)
- Final capstone project: complete ML pipeline from problem to deployment (basic)
- Portfolio preparation – GitHub / online profile with your ML projects
