Neural Networks
Build a detector with a neighbourhood
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
Build a detector centred at 2 with width 1. Its response should be 1 at the centre and fall smoothly with squared distance.
Botie needs a detector that responds near a particular example rather than increasing forever with the input coordinate.
Measure displacement from centre 2, square it, and turn it into a Gaussian response with width 1.
Examples and results
- Input coordinate
0
- Required result
0.1353
- Input coordinate
1
- Required result
0.6065
- Input coordinate
3.5
- Required result
0.3247
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 reading moves to the other side of the centre
This check uses the pieces from “Make a response centred on coordinate two”.
BOTIE
- Input coordinate
4
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 would one such detector be insufficient to describe several separated regions of interest?
A radial basis network combines local responses centred at different prototypes.
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 →