diff --git a/assets/media/learn/index.html b/assets/media/learn/index.html new file mode 100644 index 0000000..0e0565f --- /dev/null +++ b/assets/media/learn/index.html @@ -0,0 +1,484 @@ + + + + + +Manifold — the parameter landscape + + + +
+ + +
drag to rotate · top-down view = the flat 2-D map
+ + +
+
input · 2-D control
+ +
+ params + + 1 + +
+
+ + +
+
outputs
+
+
+ + +
+ + + +
+ + +
+
+ + +
+
+ + + +
loading the  NISPS  engine…
+
+ + +
+

The parameter landscape

+

placeholder copy — to be reworked

+

Two numbers go in — your X / Y control position — and a whole fistful of parameters comes + out. You can't picture a dozen dimensions at once, so picture them stacked: each slab is one + parameter, drawn as a 3-D landscape whose height at any spot is that parameter's value. One probe + reads every slab at the same control position.

+

Seen straight from above the slabs overlap into a single flat map — it looks 2-D. Tilt it and the + reveal lands: it was a stack of 3-D surfaces all along. Add parameters to grow the sandwich.

+

Every surface here is the real NISPS network sampled across the input space. 👍 keep teaches + the net that this sound belongs at this spot and the landscape bends to honour it; 👎 either pushes the + mapping away from the current sound or (in explore mode) re-rolls a fresh candidate to audition. nudge + and randomise perturb the net; undo steps back.

+
Values under the probe
+
+

← back to the instrument · animated explainers →

+
+ + + + +