LittleAIMaster Activity Pack

Deep Learning for Teens

ages 13–18 · 2 activities · about 50 minutes each

Print this and work through one activity at a time. Each one ends with something you can check, so you can tell whether the idea actually landed rather than guessing.

1. Add layers in TensorFlow Playground

Ages 11–18 · about 30 minutes

You need: A laptop and a browser

  1. Load the spiral dataset and try to separate it with one layer.
  2. Record how badly it does.
  3. Add layers one at a time, noting the loss after each.
  4. Then add far too many and watch it memorise instead of generalise.
It worked if: The teenager can describe both underfitting and overfitting from something they watched happen.

What went wrong / what surprised us:

2. Cost audit of a large model

Ages 13–18 · about 40 minutes

You need: Internet access and a calculator

  1. Look up published training-compute figures for a well-known model.
  2. Convert to an electricity estimate using a local price per kilowatt-hour.
  3. Compare that to the household's annual electricity use.
  4. Write a short position on who can afford to train models and what that concentration means.
It worked if: The teenager can connect a technical property of deep learning to a question about power and access.

What went wrong / what surprised us:

A note on tools: everything recommended for ages 13–18 is free and runs in a browser. If a product asks you to pay before your child can finish an activity, there is almost always a free equivalent.

littleaimaster.com · Deep Learning for Teens

Want the next twenty activities?

The app turns these one-off sheets into a sequence with progress you can actually see. Free to start.

Start Free in Your BrowserNo download needed · Works on this computer

Or get the mobile app

Download on theApp StoreGet it onGoogle Play
Rated 4.8Used by 1,000+ familiesFree to start · No card