What information entered the process?
Labs / Computer Science
Gradient Descent
A straight line is trying to fit a cloud of points. On the left it nudges its slope and intercept to shrink the total squared error; on the right, those same two numbers are a marble rolling downhill on the loss surface. Add your own points, change the learning rate, and step or run the descent.
Labs / Computer Science / Gradient Descent
Gradient Descent
A straight line is trying to fit a cloud of points. On the left it nudges its slope and intercept to shrink the total squared error; on the right, those same two numbers are a marble rolling downhill on the loss surface. Add your own points, change the learning rate, and step or run the descent.
Why it matters
Why explore this?
Computer science turns clear rules into reliable processes. This model lets you step through those rules and see how each decision changes the result.
Explore
Try the model
m —b —MSE —descending
Investigate
Questions to test
Predict first, try it in the model, then use what you observe to answer.
What to try
- Crank the learning rate all the way up. Why does the marble shoot off the surface instead of settling into the valley?
- Set a tiny learning rate and press Run. Is the line still improving, or has it basically stalled?
- Click to drop a single point far from the others. How much does one outlier drag the best-fit line toward it?
- Where on the loss surface does the marble slow down, and what does that tell you about the slope of the hill there?
- Switch from Rising to Scattered data. What happens to the shape of the valley when the points have no real trend?
Explain
Make sense of what happened
Trace the process one step at a time. Name the rule used at each important step, then explain why the final result follows from those rules.
Check
Before you leave
Which rule changed it?
Why did the process produce this result?
If you can answer all three using evidence from the model, you understand the main idea. If not, return to Explore and change one setting at a time.