1.2 Neural Networks Lesson

Standards & Guidelines

Lesson Overview

This lesson introduces students to a specific type of supervised learning called neural networks. Students will learn how neural networks work from a game in which they role-play different components of a neural network.

Total Lesson Time: Two 45 minute lessons

Learning Objectives: Students will be able to . . .

Label a diagram of each step in the training process of a neural network to identify feedforward, evaluation, and backpropagation.
Describe where the “learning” occurs in the process of training a neural network.
Explain that training data makes a neural network specific to a purpose.

Vocabulary Introduced: neuron, output layer, hidden layer, input layer, feedforward, feedforward neural network, evaluation, backpropagation

Pacing:

Day 1:

Opening (5 min)
Introduction to new material, terms, guided practice (17 min)
Neural Network Game, Part 1 (20 min)
Closing (3 min)

Day 2:

Opening (5 min)
Introduction to new material, terms, guided practice (15 min)
Neural Network Game, Part 2 (20 min)
Closing (5 min)

Planning Guide

Preparation Needed: 10-30 minutes each lesson

Materials:

Neural Network Activity directions
Two images
1 pencil per student
34 colored notecards
Small pieces of paper (with 9 students x 2 games) 26 yellow, 8 green and 2 pink

Prep Needed for Teaching In-Person:

Print the Neural Network Activity directions
Print the exit ticket

Log in or register to view attachments and related links, and/or join the discussion. If you are already logged in, scroll to the bottom of this page for the links.

Teacher Modifications

One of the amazing things about this curriculum is how much teachers have been involved in modifying it make it more fun, engaging, and inclusive for their students.

Click on Teacher Modifications in the Navigation menu to see what teachers of made!

Activity Usage

License: CC-BY-NC under Creative Commons

These materials are licensed as CC-BY-NC 4.0 International under creative commons. (For more information visit https://creativecommons.org/licenses/by-nc/4.0/). This license allows you to remix, tweak, and build upon these materials non-commercially as long as you include acknowledgement to the creators. Derivative works should include acknowledgement but do not have to be licensed as CC-BY-NC. People interested in using this work for for-profit commercial purposes should reach out to Irene Lee at [email protected] for information as to how to proceed. Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)

Attribution:

The "Neural Network Game" was developed by Irene Lee for Project GUTS in 2019. It was based on the “Human Neural Network Game” developed by Catherine Schuman, Steven Young, Thomas Proffen, Dasha Herrmannova of Oak Ridge National Laboratory for the TechGirlz program (TechGirlz 2018). The "Neural Network Game" augmented the "Human Neural Network Game" by including evaluation and back propagation. The "Neural Network Online Game" was created for the DAILy Curriculum for Middle School Students by Irene Lee with support from NSF award #2022502.