Machine Learning & Python Programming

Duration: 2 Months
Mode: Physical
Instructor: Laiba Abbas

Course Overview

This course offers a hands-on introduction to Artificial Intelligence (AI), focusing on real-world applications rather than theory. students will gain practical experience in machine learning, deep learning, computer vision, NLP, and large language models, while also learning how to deploy and share AI solutions through modern tools and frameworks.

Course Objectives

Grasp essential AI concepts: Machine learning, deep learning, computer vision, NLP, and the unique role of agentic AI.
Develop coding proficiency: Write and debug AI code in Python using tools like Jupyter, scikit-learn, PyTorch/TensorFlow, HuggingFace, and more.
Work with real-world data: Prepare, visualize, and process image and text datasets for AI projects.
Build and evaluate models: Train, test, and save machine learning and deep learning models.
Solve problems using agentic AI: Understand and implement basic AI agents for workflows and automation.
Deploy apps: Package, deploy, and demonstrate practical AI apps using Streamlit, FastAPI/Flask.

Module 1: Foundations of Practical AI

Course orientation & expectations
Overview of AI concepts (non-theoretical)
Setting up coding environments (Jupyter, Python, Colab)
First hands-on coding: basic Python for AI

Module 2: Python Essentials for AI

Variables, data types, and control flow
Functions, lists, dictionaries
File handling and simple data manipulation

Module 3: Data Preparation & Exploration

Loading datasets (CSV, images, text)
Data cleaning & preparation
Simple data visualization (matplotlib/seaborn)

Module 4: Classical Machine Learning

What is machine learning? Practical examples
Building and evaluating ML models with scikit-learn: classification, regression
Train/test split, basic model metrics

Module 5: Core Deep Learning (Images & Text)

Neural networks: hands-on walkthrough (with Keras or PyTorch)
Building a simple image classifier (e.g., MNIST, CIFAR-10)
Implement ANN, CNN and RNN models
Understanding model training, evaluation

Module 6: Computer Vision Fundamentals

Intro to OpenCV & Image Basics
Image Preprocessing & Transformations
Use OpenCV for face/object detection
Implement transfer learning using ResNet/MobileNet

Module 7: NLP (Natural Language Processing)

Text data handling, basic preprocessing (tokenization, embeddings, Stop Words)
Apply ML and DL models for text classification
Introduction to transformers and HuggingFace
Mini-project: sentiment analysis or text classification

Module 8: Deploying & Sharing Your AI

Save and load ML/DL models for reuse (joblib, pickle, model.save()).
Build simple web apps with Streamlit for interactive demos.
Serve models as APIs using FastAPI/Flask; (optional) connect to Next.js for advanced frontends.