Neural Networks
Give two neurons different jobs
BOTIE
Examples, experiments and workspace controls
Connect a tool's inputs to see what it produces. You can try a branch before connecting it to Result.
Try your own inputs
Use a copy of the example to try your own data. Keep the problem's assumptions in mind, and predict the effect of a change before checking the output. You can also add another branch to compare two ways of doing the calculation.
Context for this challenge
What can two neurons tell us about the same light pattern? Return the combined brightness first and the left-minus-right contrast second. Keep both responses together in that order.
Botie needs both total brightness and left-right contrast from the same two sensors. Keeping both responses avoids losing either kind of information.
Feed both sensor readings to a brightness calculation and a contrast calculation, then keep the outputs in the requested order.
Examples and results
- Left light sensor
1
- Right light sensor
3
- Required result
- 04
- 1-2
- Left light sensor
3
- Right light sensor
2
- Required result
- 05
- 11
Try a fresh construction
This clears this draft, including its undo history. Earlier successful attempts stay recorded. Build again without opening hints to record an independent attempt.
Stuck? Inspect a worked construction
The tools below form one possible solution. You can assemble it, follow its signals, and undo that change to return to your own construction.
Assumptions and test precision
This is a small construction problem. The lesson explains the assumptions and the parts of the full method that this example leaves out. Numerical tests allow a difference of 0.001. Lists and structures must also have the right shape.
The stronger light moves to the right
This check uses the pieces from “Branch one light pattern into two responses”.
BOTIE
- Left light sensor
0.5
- Right light sensor
2.5
Use a number, text, or an array matching the requested result. For a matrix, put each row in brackets. Saving your prediction runs your current construction on these inputs and checks the earlier examples too.
Build a construction in the workspace above first. This case will test those pieces.
Why can patterns with equal total brightness still need different downstream responses?
A layer carries multiple measurements of the input forward together.
This is a small construction problem. The lesson explains the assumptions and the parts of the full method that this example leaves out.
Work through the Python challenges →