← Back to QuantegyAI

Neural Networks & Deep Learning

Eight interactive modules · about 3–4 hours · Course 3 (Machine Learning Foundations) is the prerequisite. No coding required.

Track your progress. Sign in to save module completion and your mastery scores across devices. Your progress also saves on this device automatically. Open the portal →

This course takes the one idea you met at the end of Machine Learning Foundations — a model is a weighted sum trained by gradient descent — and grows it into a deep neural network. You will start from a single neuron, stack neurons into layers, watch a network make a forward pass, then train it live: gradient descent, backpropagation, the effect of depth, and the discipline that stops a network from memorizing instead of learning.

Every module runs entirely in your browser and is extensively hands-on: you will adjust a neuron’s weights and observe its output change, bend a decision boundary with an activation function, vary the learning rate and observe the loss curve converge or diverge, step through backpropagation one gradient at a time, and train a real network on a spiral dataset until it separates the two classes. Each module also presents the corresponding Keras / PyTorch code for later recognition. Each module concludes with a short mastery check; passing it marks the module complete.

The building block

Module 1

From a Neuron to a Network

The artificial neuron: a weighted sum plus a bias plus an activation. Activity: drag the weights and bias and watch one neuron act as an AND / OR gate. AI anchor: every deep model is millions of these.

Module 2

Activation Functions

Sigmoid, tanh, ReLU — and why a network without them is equivalent to a single linear model. Activity: plot each activation and stack two layers to see non-linearity produce a curved boundary. AI anchor: ReLU and the resurgence of deep learning.

Putting neurons together

Module 3

The Forward Pass

Stack neurons into layers and push data through. Inputs → hidden layer → output, and the decision regions a small network can draw. Activity: feed points through a live 2-layer network and watch every value light up. AI anchor: inference.

Module 4

Gradient Descent in Practice

How a network learns: a loss to minimize, a learning rate to tune, and a training loop. Activity: train a real net live, watch the loss curve fall, and crank the learning rate until it overshoots. AI anchor: every model is trained this way.

Module 5

Backpropagation Intuition

The chain rule, working backward to give every weight its share of the blame. Activity: step one training iteration — forward to the loss, backward through the gradients — and watch which weights move most. AI anchor: the algorithm behind all of it.

What makes it deep learning

Module 6

What Depth Buys You

Why stack layers at all? Features built on features. Activity: train a net on a tangled spiral and add hidden layers with a depth slider — watch a boundary no straight line could ever draw appear. AI anchor: representation learning.

Module 7

Training Real Networks

Large networks tend to memorize their training data. Activity: observe training loss decrease while validation loss increases, then enable weight decay, dropout, and early stopping and observe the gap close. AI anchor: every production model must address this.

Project

Module 8 · Project

Train a Network End-to-End

Put it all together: pick a dataset, set the architecture and learning rate, click Train, and drive a network from random noise to a confident classifier — reading the loss curve and accuracy as it learns. A synthesis check ties every module together.

Capstone

Capstone

Build a Concept Manipulative

Put it all together: build a single-page interactive that teaches one Deep Learning concept, then submit it for grading and your certificate.

Why this matters next A neural network that turns inputs into a useful internal representation is exactly what powers a large language model (Course 5). An LLM is a very deep network trained by the same gradient descent and backprop you just used — only on text, at enormous scale. Master the trunk here and the giants make sense.

← Back to QuantegyAI