Classical Machine Learning
Keep the kernel coefficients in check
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
This toy kernel matrix is the identity. With a ridge penalty of 1, build the operation that solves each independent coefficient equation.
The identity kernel makes each coefficient equation independent. Botie can inspect ridge shrinkage here before confronting a coupled kernel system.
Add the supplied penalty to the identity contribution of one, then divide every target by that shared denominator.
Examples and results
- Training targets
- 02
- 14
- 2-2
- Ridge penalty
1
- Required result
- 01
- 12
- 2-1
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
Elementwise division is valid here because the kernel matrix is the identity. A general kernel requires solving the coupled linear system. Numerical tests allow a difference of 0.001. Lists and structures must also have the right shape.
A stronger penalty with an identity kernel
This check uses the pieces from “Solve the independent regularised coefficient equations”.
BOTIE
- Training targets
- 03
- 1-6
- 20
- Ridge penalty
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.
Which property of the kernel makes elementwise division valid here, and why would nonzero off-diagonal entries change the task?
A closed-form shortcut must retain its structural assumptions; general kernel ridge solves a coupled system.
Elementwise division is valid here because the kernel matrix is the identity. A general kernel requires solving the coupled linear system.
Work through the Python challenges →