Deep Learning
Fundamentals

The complete beginner path. Learn how neural networks actually work, from a single neuron to a full network that classifies images. No prior experience needed.

⏱ ~12 hours total
📚 17 lessons
✦ All Free

What you'll learn

By the end of this path, you'll understand how neural networks work from the ground up, be able to build and train your own models in PyTorch, and have the vocabulary to read research papers and follow ML news intelligently.

Module 1: The Basics

What is a Neural Network?

The biological inspiration, the mathematical abstraction, and why neural networks are so powerful.

Free 25 min

Perceptrons: The Building Block

The single neuron model — weights, biases, and the dot product. Build one from scratch in Python.

Free 30 min

Activation Functions Explained

Sigmoid, ReLU, tanh, and friends. Why non-linearity is the secret sauce that makes deep learning work.

Free 20 min

Loss Functions: How Do We Measure Error?

MSE, Cross-Entropy, and why choosing the right loss function matters for what you're trying to solve.

Free 25 min

Module 2: Training

Gradient Descent Visualized

The optimization algorithm at the heart of all deep learning. Watch gradients flow in an interactive demo.

Free 35 min

Backpropagation from Scratch

The chain rule made simple. Implement backprop manually — you'll never fear it again.

Free 45 min

The Learning Rate: Most Important Hyperparameter

Why too high breaks training, too low wastes time, and how to find the sweet spot.

Free 20 min

Mini-Batch SGD & Optimizers

From vanilla SGD to Adam. Why modern optimizers train faster and more reliably.

Free 30 min

Module 3: Building Real Networks

Multi-Layer Perceptrons (MLPs)

Stack layers, add depth, gain expressive power. Architecture design principles for beginners.

Free 30 min

Overfitting & Regularization

Why models that look great in training fail in the real world — and how to fix it with dropout, L2, early stopping.

Free 35 min

Batch Normalization

The surprisingly powerful normalization trick that stabilizes training and allows deeper networks.

Free 25 min

🏆 Your First Neural Network in PyTorch

Put it all together. Build, train, and evaluate an MNIST digit classifier. Full working code included.

Free 60 min

Ready to go deeper?

→ Computer Vision Path → NLP & Transformers