What is this?

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

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