Training a Neural Network (Computer Science)

Lesson notes

Overview

Forward pass, loss, backpropagation and a weight update repeat for many epochs. This topic is rated advanced and is number 107 of 117 in Computer Science. Deeper models, formal results and harder reasoning.

What you are seeing

The panel above shows the steps of a process, laid out in order. Click a step to see what happens next. The animation is drawn live from the model, so everything you see responds to the sliders. Press Space to pause, use Restart to replay from the start, and change the speed to slow down quick events.

In depth

Training repeats a cycle: a forward pass feeds a batch of data through the network to produce predictions, a loss function measures the error, backpropagation uses the chain rule to compute the gradient of the loss with respect to every weight, and an optimiser such as gradient descent updates the weights to reduce the loss. One pass through all the data is an epoch, and training takes many epochs. Validation data checks for overfitting.

Reading the relationship

The expression "backpropagation" is a compact summary of the idea. It uses the symbols b, a, c, k, p, r; name what each one stands for before you start. Then use the sliders to see how changing one quantity changes the others.

A guided exploration

1. Run the animation once with the default settings and describe in words what happens. 2. Change one slider at a time and note which quantity responds most. 3. Push each slider to its extreme and decide whether the result still makes sense.

Try this

Try to explain why the pattern holds, not just what it is. Look for limiting cases and what happens at the edges.

Common pitfalls

Test small inputs by hand and then the largest ones. Off-by-one errors and forgetting how cost grows with input size are the most common traps.

How it connects

It builds on “Recommendation Systems”, the topic before it in Computer Science. Once you are comfortable, continue with “Convolutional Neural Networks”.

Why it matters

Computing ideas decide how fast, how safely and how well software can solve problems.

Where you might use it

Revising “Training a Neural Network” before a class, exam or certification
Choosing the right algorithm or data structure when writing software or apps
Debugging programs and judging how fast or how safely code will run at scale
Understanding how search engines, games, phones and AI systems make decisions

Frequently asked questions

What is Training a Neural Network?

Forward pass, loss, backpropagation and a weight update repeat for many epochs. It is an advanced topic in Computer Science.

How do I use the Training a Neural Network simulation?

The panel at the top shows the steps of a process, laid out in order. Click a step to see what happens next. Move the sliders one at a time, then press Space to pause the animation and look closer.

What does the formula mean?

The expression backpropagation packs the idea into symbols. Name each symbol first, then change one quantity with the sliders and see which others respond.

Who is this topic for?

Deeper models, formal results and harder reasoning. If the quiz feels hard, reread the lesson notes and try the previous topic first.

What should I learn before this?

Start with “Recommendation Systems”, the previous topic in Computer Science. Each topic in a subject builds on the ones before it.

How do I track my progress?

Press “Mark as learned” on this page. Progress is stored only in this browser and is never sent anywhere. The Browse page can show topics you have learned or still need to learn.