Classical Machine Learning
Repair what the first model missed
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
The correction model predicts what the earlier model missed. Add a quarter of its prediction to the existing prediction.
A fitted correction model estimates what the earlier prediction missed. Botie will add a controlled fraction of that correction.
Scale the residual-model prediction by 0.25 and add it to the earlier model's prediction.
Examples and results
- Earlier prediction
2
- Fitted residual prediction
4
- Required result
3
- Earlier prediction
1
- Fitted residual prediction
8
- 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.
The next learner recommends a large downward correction
This check uses the pieces from “Apply a quarter of the fitted correction”.
BOTIE
- Earlier prediction
10
- Fitted residual prediction
-8
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 this operation not an equal-weight average of two independent predictions, and what would have to be learned before another stage?
Boosting adds models sequentially to correct remaining error, with each stage depending on the current prediction.
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 →