NISPS lets you teach a neural network how to map a 2D joystick position to a rich set of visual or audio parameters. Move the joystick, shape the outputs you want, and the network learns your preferences in real time.
+
+
+
+
How it works
+
A small neural network takes your joystick X/Y position as input and produces dozens of output parameters. You teach it by either:
+
+
Examples — set the parameter sliders to what you want at a given joystick position, add the example, then hit Train. Do this a few times from different positions and the network interpolates between them.
+
Feedback (RL) — move the joystick around. If you like what you see/hear, press + (keep this). If you don't, press − (explore more). The network gradually learns what you prefer.
+
+
+
+
+
What to expect
+
+
Moving the joystick changes all outputs in real time through the network
+
Randomize shuffles the network weights — instant new mapping
+
Train fits the network to your saved examples
+
+ / − feedback nudges the network: + reinforces the current mapping, − adds exploration noise
+
Switch between Visual (particle flow field) and Synth (C15 synthesizer) output modes
+
The heatmap bar at the top shows all output parameters at a glance
+
+
+
+
+
Controls
+
+
Touch / Mouse
+
Drag joystick
Move through parameter space
+
+ / − buttons
Positive / negative feedback
+
Bottom bar
Train, Randomize, Clear, Follow mode
+
Keyboard
+
1
Negative feedback (−)
+
2
Positive feedback (+)
+
Gamepad (Steam Deck, Xbox, etc.)
+
Left stick
Joystick control
+
LB (left bumper)
Negative feedback
+
RB (right bumper)
Positive feedback
+
A
Train
+
X
Randomize
+
B
Clear examples
+
+
+
+
+
Tips
+
+
Start with Randomize a few times to hear/see different mappings, then use feedback to refine
+
Use Follow mode to let the joystick wander automatically while you give feedback
+
In Synth mode, press the play button (top left) to start audio, then explore
+
Tap a heatmap cell to see which parameter it controls