Neural Networks
Follow the effect backwards
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
Return prediction minus target for the current input and weight.
A prediction is wrong, but changing every weight arbitrarily would not tell us how to improve it. Let's follow one weight's effect through a tiny model. The weight changes the prediction, and the prediction changes the loss. Combining those two local effects tells us how that weight affects the loss.
Inspect the component calculation
Subtract(
Starting value: Multiply(
Value: Input
Multiplier: Current weight
)
Value to remove: Target
)Examples and results
- Input
2
- Current weight
1
- Target
5
- Required result
-3
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.
Your last tested pieces can start the full construction. An existing draft there keeps its own pieces.
A negative input reverses the gradient's sign
This check uses the pieces from “Trace the weight's route to the loss”.
BOTIE
- Input
-2
- Current weight
1
- Target
2
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 is the input needed after you already know the prediction error?
Gradients account for how strongly each parameter influences the error, not only the error's size.
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 →