Full Curriculum
All Lessons
Every module, every lesson, all in one place. Start from the beginning or jump to any topic.
Module 1
What is Machine Learning?
Understand what ML is, why it matters, and how it differs from traditional programming.
What is Machine Learning?
Discover what machine learning actually is, how it differs from regular programming, and why it's one of the most important technologies of our time.
Types of Machine Learning
Learn the three main types of machine learning — supervised, unsupervised, and reinforcement learning — with intuitive examples.
Real-World ML Examples
See exactly how machine learning is applied in products you use every day — and understand the data behind each use case.
Module 2
Python for Machine Learning
Learn just enough Python to start building ML models — no prior coding experience needed.
Variables & Data Types
Learn the fundamental building blocks of Python — variables, numbers, strings, and booleans — with hands-on examples tailored for ML.
Lists & Dictionaries
Master Python's two most important data structures — lists and dictionaries — which are used constantly in ML for storing datasets, labels, and configurations.
Loops & Functions
Learn how to repeat actions with loops and organize reusable code with functions — two tools you'll use in every ML project.
NumPy Basics
Discover NumPy — the foundational array library of ML. Learn to create arrays, perform fast math, and manipulate shapes — all essential for data pipelines.
Module 3
Data Exploration & Visualization
Explore, clean, and visualize real datasets using Pandas, Matplotlib, and Seaborn.
Pandas DataFrames
Master Pandas — Python's data manipulation powerhouse. Load, inspect, filter, and transform tabular data just like a spreadsheet, but with code.
Data Cleaning
Real-world data is messy. Learn to handle missing values, remove duplicates, fix data types, and detect outliers — essential skills before any ML project.
Matplotlib & Seaborn
Visualize data like a pro using Matplotlib and Seaborn. Learn to create histograms, scatter plots, heatmaps, and more to gain insights before modeling.
Module 4
Classical Machine Learning
Master regression, classification, clustering, and more using scikit-learn.
Linear Regression
Understand and implement linear regression — the simplest and most foundational ML model. Predict continuous values and learn the math behind it.
Logistic Regression
Despite its name, logistic regression is a powerful classification algorithm. Learn to predict probabilities and classify data into categories.
Decision Trees
Learn decision trees — one of the most interpretable ML models. Understand how they split data, what overfitting means, and how to control tree depth.
Random Forests
Random forests combine hundreds of decision trees to create a far more powerful and robust model. Learn ensemble learning and why it almost always beats a single tree.
Clustering with K-Means
Discover unsupervised clustering — grouping data without labels. Learn K-Means, how to choose the right number of clusters, and real-world applications.
Support Vector Machines
Learn SVMs — powerful classifiers that find the optimal boundary between classes. Understand kernels, the margin concept, and when SVMs shine.
Module 5
Neural Networks & Deep Learning
Build and train neural networks from scratch and with PyTorch.
What is a Neuron?
Understand the building block of all neural networks — the artificial neuron. Learn how it mimics the brain, applies weights, and produces an output.
Forward Pass & Backpropagation
Understand how neural networks learn — the forward pass generates predictions, backpropagation computes gradients, and gradient descent updates weights.
Introduction to PyTorch
Get started with PyTorch — the leading deep learning framework. Learn tensors, autograd, and how PyTorch makes building neural networks clean and enjoyable.
Building Your First Neural Network
Build, train, and evaluate a real neural network in PyTorch from scratch — classifying handwritten digits with the MNIST dataset.
Module 6
NLP & Large Language Models
Process text, understand embeddings, and leverage transformers and HuggingFace.
Text Preprocessing
Learn how to prepare raw text for ML models — tokenization, stopword removal, stemming, lemmatization, and converting text to numerical features.
Word Embeddings
Go beyond Bag-of-Words with word embeddings — dense vector representations that capture semantic meaning. Learn Word2Vec, GloVe, and contextual embeddings.
Transformers Explained
Understand the architecture behind ChatGPT, BERT, and every modern language model. Learn attention mechanisms, self-attention, and the transformer architecture.
Using HuggingFace
Put state-of-the-art NLP models to work in minutes. Learn the HuggingFace pipeline API, AutoTokenizer, AutoModel, and how to fine-tune a model on your own data.
Module 7
Computer Vision
Work with image data, build CNNs, apply transfer learning, and detect objects.
Image Data Basics
Learn how computers see images as tensors of numbers. Understand channels, shapes, pixel values, and how to prepare image data for neural networks.
Convolutional Neural Networks
Build a CNN from scratch. Understand convolutions, filters, feature maps, pooling, and train a network to classify images on CIFAR-10.
Transfer Learning
Use a model trained on millions of images to solve your own task with just hundreds of examples. Learn feature extraction, fine-tuning, and when to use each strategy.
Object Detection Basics
Go beyond classification. Learn how to detect and locate objects in images with bounding boxes, understand IoU metrics, the YOLO concept, and use a pretrained Faster R-CNN.