Python for AI and Machine Learning

Name: Python for AI and Machine Learning
Rating: 4.0 (182 reviews)

Master Python for Artificial Intelligence and Machine Learning with TensorFlow, PyTorch, and Scikit-Learn.

Created bySenior Assist Prof Azad Rasul

Last updated 2/2026

English

What you'll learn

Master Python programming for AI and ML applications.
Build machine learning models with Scikit-Learn (e.g., Random Forest).
Develop deep learning models using TensorFlow and PyTorch.
Process and visualize data with Pandas, NumPy, and Matplotlib for AI/ML tasks.

Course content

12 sections • 42 lectures • 5h 31m total length

Welcome and course overview3:19
What is Artificial Intelligence?4:19
What is Machine Learning?6:13
Why Python is the Top Choice for AI & Machine Learning?2:47
Setting up Python1:51
Learn how to download and install Miniconda to set up Python for AI and machine learning, using conda and pip, selecting the right version, and setting Python 3.9 as default.
Setting up your Python environment for AI/ML3:53
Installing and Running Jupyter Notebook.3:17
Introduction

Python basics: Variables, data types, and operators3:02
Control flow: If statements, loops, and exceptions1:19
Functions in Python.2:19
Learn how Python functions act as blocks of code you call repeatedly, with and without arguments, using print to display messages like hello from Python tutorial.
Modules in Python.2:32
Working with lists, dictionaries, and sets for data processing.14:02
Learn how lists, dictionaries, and sets empower data processing in ai and ml by wrangling data, normalizing sensor data, encoding labels, and deduplicating while preparing training and test sets.
Python Programming Fundamentals

Introduction to NumPy for numerical computing.10:26
File Handling in Python3:37
Managing Directories in Python2:49
Explore managing directories in Python using the os module to get and change the current working directory, expand the home directory, list files, and check path existence.
Data manipulation with Pandas: DataFrames, filtering, and merging.7:35
Import and Clean Datasets in Jupyter Notebook with Pandas12:48
NumPy and Data Manipulation with Pandas

Convolutional neural network (CNN) with PyTorch for image classification13:15
Build a convolutional neural network for satellite image classification using PyTorch, training on the Neurosat dataset with ten land-use classes and a pre-trained ResNet-50, 80/20 train-test split.
Using GPUs for faster training9:45
Set up a GPU-enabled TensorFlow 2.1 environment with CUDA toolkit. Verify GPU availability in Jupyter and compare GPU versus CPU performance on matrix multiplication and a neural network.
Deep Learning

Air Quality Monitoring in India: A Python and ML Case Study Part 19:10
Air Quality Monitoring in India: A Python and ML Case Study Part 214:07
This course uses python for ai and ml to monitor air quality in India, remove outliers with the iqr method, impute missing data, and compute aqi from so2, no2, spm.
Air Quality Monitoring in India: A Python and ML Case Study Part 318:45
Air Quality Monitoring in India: A Python and ML Case Study Part 411:25
Air Quality Monitoring

Requirements

No programmingA computer with internet access (Windows, macOS, or Linux).
No prior programming or AI/ML experience required—everything is taught from scratch.
A Google account for Google Colab (free) and optional GPU access.
Enthusiasm to learn and build exciting AI/ML projects. experience needed.

Description

Welcome to Python for AI and Machine Learning, the ultimate course to master Python for building cutting-edge artificial intelligence (AI) and machine learning (ML) models! This comprehensive 25+ hour course is crafted for complete beginners and aspiring professionals, requiring no prior coding experience. You’ll progress from Python fundamentals to advanced AI techniques using industry-standard tools like TensorFlow, PyTorch, and Scikit-Learn, guided step-by-step to ensure success.

Through 4+ hands-on projects—including a crop health predictor, image classifier, air quality forecaster, and a custom ML application—you’ll gain practical skills to create a job-ready portfolio. Learn to process and visualize data with Pandas, NumPy, and Matplotlib, and train models in the cloud using Google Colab with GPU support. The course applies AI/ML to real-world challenges in industries like agriculture, healthcare, and environmental science, making it relevant for diverse learners.

Taught by Dr. Azad Rasul, a geospatial data scientist and Assistant Professor with over 150,000 students mentored, this course offers clear explanations, practical projects, and career-focused guidance for high-demand data science and AI roles.

Whether you’re aiming to land a data science job, enhance your current role, or explore AI innovations, this course equips you with the tools and knowledge to succeed. Join a global community of learners and start building impactful AI solutions today!

Who this course is for:

Complete Beginners
Aspiring Data Scientists and AI Engineers
Professionals in Related Fields
Students and Researchers
Developers Transitioning to AI/ML

Python for AI and Machine Learning

What you'll learn

Explore related topics

Course content

Introduction7 lectures • 26min

Python Programming Fundamentals5 lectures • 23min

Data Handling with Pandas and NumPy5 lectures • 37min

Data Visualization with Matplotlib and Seaborn3 lectures • 28min

Introduction to Machine Learning with Scikit-Learn3 lectures • 29min

Deep Learning with TensorFlow and PyTorch2 lectures • 23min

Cloud-Based AI with Google Colab5 lectures • 50min

Capstone Project 1: Crop Health Prediction1 lecture • 9min

Capstone Project 2: Air Quality Monitoring4 lectures • 53min

Capstone Project 3: Counting Plants Using Computer Vision Techniques1 lecture • 10min

Requirements

Description

Who this course is for: