Neural Networks
Carry something into the next step
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
Move the same energy from an early audio frame to a later one. Predict which running totals will change and which will stay the same. The final total alone cannot tell us when that sound arrived.
Context for this challenge
How much sound energy has arrived so far? Build a running total from the energy measured in each audio frame. Return the total after every frame, preserving its order.
A quiet audio frame does not reveal how much sound came before it. Botie will carry a running energy total from one frame to the next.
Produce the cumulative energy after every frame while preserving the sequence order.
Examples and results
- Energy per audio frame
- 01
- 12
- 21
- 33
- Required result
- 01
- 13
- 24
- 37
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.
Silent frames between bursts of energy
This check uses the pieces from “Carry accumulated energy through the audio frames”.
BOTIE
- Energy per audio frame
- 00
- 12
- 20
- 30
- 41
- 50
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 earlier-frame details cannot be recovered from only the final energy total?
A recurrent state retains a chosen summary of history, not necessarily the full sequence.
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 →