Learning objectives
Students will be able to:
-
01
Hidden layers
Trace a forward pass through hidden layers, with weighted sums, biases and an activation function, and predict each middle node's value before the network works it out.
-
02
Back propagation
Follow the error back across each weight, see it add up at a node that feeds several outputs, and see it stop at a node the activation function held at zero.
-
03
Gradient descent
Apply the update rule, input value × error × learning rate, and explain why a learning rate that is too large makes training overshoot or blow up.
-
04
Training vs. testing
Use testing data the network has never seen to judge whether it has truly learned, and compare how well it learned each of its outputs.
Lesson plans
Ready-made plans for a day, three days or a week, with what to say, what to watch for and what to ask afterwards.
-
Forward, Backward, Update
A single class on the three steps every modern AI repeats billions of times as it trains. Students push numbers forward through a hidden layer, send an error back, and work out a weight update by hand.
Open lesson plan -
The Algorithm Behind Modern AI
Three days, one for each step of training: the forward pass through hidden layers, back propagation of the error, and gradient descent. The third day ends on a network that learns two answers and is judged on data it has never seen.
Open lesson plan -
Building a Network That Learns
A week-long unit on the full algorithm behind modern AI, from the forward pass to gradient descent, ending on a network that predicts the next word in a sentence. Every lesson on the high school page is used, along with its three example networks.
Open lesson plan
Lessons to explore
Here are 9 lessons, in order. Each one opens up the app. You may also find all iiNNoo lessons here.
-
The Talent Show Predictor
This network predicts the audience at a school talent show. The input values are the number of acts and posters put up. Each input value reaches both middle nodes, and both middle nodes reach the output value. In the first round, predict each middle node value, then the output value. Enter your answer when asked.
Open lesson -
The Birthday Book Predictor
On your birthday, you get money that you can use to buy books. The input value is the dollars and the output value is the books. You owe your friend $10, so the middle node's bias is -10. Each book costs $5. Predict the middle node, then the output value, in the first two rounds. The activation function holds anything below zero at zero.
Open lesson -
The Street Musician Predictor
This network predicts what a street musician collects. The input values are the hours played in the morning and in the evening. The output value is the money in the hat. The input values never receive an error, because nothing can change them. Predict the error that reaches the middle node, where it stops.
Open lesson -
The City Park Predictor
This network predicts the litter left in a city park. The input values are the food trucks and snack carts. The output values are the wrappers and bottles left behind. Each middle node collects the errors from both output values. Predict the error that reaches each middle node in the first two rounds.
Open lesson -
The Yawn Predictor
This network predicts a student's yawns in class. The input values are the hours slept and the hours needed. Too much sleep or too little brings yawns. At most one middle node is above zero each round, and only that one can receive an error. Predict the error that reaches each middle node in the first two rounds.
Open lesson -
The Pet Rescue Predictor
This network predicts a day at a pet rescue. The input values are the dogs and the cats waiting for homes. The output values are the visitors and the adoptions. The bottom middle node's bias holds it at zero every day. Predict the error that reaches the top and bottom middle nodes in the first two rounds.
Open lesson -
The Recycling Drive Predictor
This network predicts the bags of cans a school recycling drive collects. The input value is the number of classes taking part. The output error comes back to both middle nodes. In round 1, predict the output error, both middle errors, and the adjustment to the weight to the top middle node. The learning rate is 0.02.
Open lesson -
The Test Score Predictor 02
This network predicts a test score. The input values are the hours of study and of sleep. The output value is the score. Its weights blow up as it learns. Find a learning rate that keeps them under control. Figure out which learning rate works, then run it again.
Open lesson -
The Harbor Predictor
This network learns how busy a harbor will be, through a middle layer. The input values are the sunshine and the wind, from 0 to 5. The output values are the swimmers and sailboats. Decide which of the two answers it learns better. Train it on all the days, then switch to testing data and compare.
Open lesson
Example networks
Complete networks to run and explore freely, with no task to finish.
-
The Traffic Light Decider
This network decides how long each of 3 roads gets a green light. The input values are the cars waiting on the north, east and south roads. The output values are the 3 green light times. Each road has its own path through a middle node. Click on a connection to see its weight.
Open lesson -
The Air Quality Monitor
This network turns 4 roadside readings into 4 pollutant levels. The input values are the traffic, wind, temperature and humidity, each scored from 0 to 5. The output values are the dust, nitrogen, ozone and carbon. With 255 steps a round, try swift mode with this one. Train it, then switch to testing data to confirm it learned correctly.
Open lesson -
The Next Word Predictor
This network predicts the next word in a sentence, like a tiny version of the AI that writes text. The input value is a word, and the output values show which word comes next. It learns from 7 short sentences, such as “the dog is cute” and “the sky is blue.” Train it in swift mode, then switch to testing data. Which words does it expect after “is”?
Open lesson
Ready to bring iiNNoo to your classroom?
Questions or ideas? Email us at support@iinnoo.app.
Start Learning How AI Learns