CAS STUDIES · INTERACTIVE LEARNING
Deep learning,
made visible.
Build neural networks from first principles. Read the mathematics, manipulate the parameters, and follow every number through the architecture.
Start the first lesson ↓Weighted sums. Sigmoid activations.
One forward pass at a time.
THE SERIES
Interactive lectures
Introduction of MLP Forward Propagation
Understand the multilayer perceptron as a chain of weighted sums and sigmoid activations. Inspect every neuron, edit the parameters, and compute a complete 4–3–2–1 forward pass.
MLP Backpropagation: Individual Derivatives, Chain Rule & Weight Updates
Walk the 4–3–2–1 network in reverse. Build visual intuition with handwritten derivatives, master the 4 individual derivatives, trace how the chain rule multiplies sensitivities across layers, and update every weight with gradient descent.
Gradient Descent on a 3-Layer Network: Every Weight, Every Update Rule
Derive all 15 parameter updates of a 2–2–2–1 linear network by hand. Write the complete chain rule for each weight, simplify it step by step, check every gradient with live numbers, and watch the network train.
Gradient Math & Chain-Rule Intuition: Resolving Every 4–3–2–1 Derivative
See how partial derivatives physically measure frozen-knob slopes before expanding all 26 weight and bias gradients on a 4–3–2–1 linear network step by step—including why Layer 1 splits and sums two paths.
Gradient Lab: Build an MLP & Trace Every Gradient
Design your own multilayer perceptron neuron by neuron, then click any weight, bias, or neuron to trace its forward value, its gradient, and every chain-rule path to the loss. Step through propagation and watch gradient descent train the network live.
Diagrams and calculations stay connected.
Change real parameters and observe the result.
Notation follows understanding—not the other way around.