Add WasmIML.extractWeights() and WasmIML.createWithWarmStart() to preserve
learned joystick mappings across output-count changes; resizeMLP() now
transfers hidden-layer weights and shared output nodes instead of cold-starting.
Expose inferBatch, trainEx, moveWeightsEx, evalLoss, and getLayerStats
from the WASM binary into the JavaScript layer:
- inferBatch: batch inference for heatmap sampling
- trainEx: replaces train() with per-iteration loss history capture
- moveWeightsEx: native output pin mask support (removes save/restore hack)
- evalLoss: compute loss without updating weights
- getLayerStats: per-layer weight statistics (meanAbs, maxAbs, dead/sat fracs)
Worker also upgraded to trainEx, returning full lossHistory in payload.
- Add window.__nisps debug probe (gated on ?debug=1) exposing iml state,
getOutputs/getLoss/getWeights/getExampleCount, and action triggers
(thumbsUp/thumbsDown/train/randomise/clearExamples/saveState)
- Fix WasmIML bug: this.dataset was a plain object; import Dataset and
use new Dataset(100) so computeWeights() is available for training
- Fix WasmIML.addExample/clearDataset to use Dataset API methods
- 44 Playwright e2e tests across 4 spec files:
- ml-engine.spec.js: WASM inference bounds, training loss, thumbs
up/down behavior, async training, example capture semantics
- ui-interactions.spec.js: drawer open/close, mode switching,
heatmap bar counts, preset chips, keyboard shortcuts (1/2/Z)
- input-pipeline.spec.js: input→output variation, clamping, joystick
drag, post-training output bounds across the full input space
- persistence.spec.js: URL params (?preset, ?spread), localStorage
round-trip, saveState probe
Add Dataset.computeWeights() with three modes:
- global: exponential recency decay (newest examples weighted higher)
- local: spatial suppression of older examples near the current input
- combined: both applied together
IML and WasmIML now compute weights on every train() call using the
active mode. Exposes recencyBias, weightingMode, localRadius properties.
WASM worker path passes sampleWeights through to C++ via the new binding.
Compile nisps-core C++ MLP to WASM (36KB) and use it as the ML engine
in the playground, replacing the JavaScript port for inference, training,
and weight manipulation.
- Add extern "C" WASM bindings with spread-aware drawWeights/moveWeights
- WasmIML class is a drop-in replacement for the JS IML
- Inference runs on main thread via WASM (fast, synchronous)
- Training runs in a Web Worker with its own WASM instance (non-blocking)
- Interactive training (thumbs-up, train button) no longer freezes UI/audio
- Preset loading and state restore still use sync training
Add ?spread=0-1 URL param that controls weight initialization scaling,
RL noise scaling per layer, noise cap, and weight decay to prevent
sigmoid output saturation. At spread=0 (original behavior) weights are
uniform [-1,1] and outputs polarise near 0/1. At spread=1 weights use
Xavier scaling (1/sqrt(fan_in)), noise is proportionally reduced, and
10% weight decay per thumbs-down prevents unbounded magnitude drift.
Also fix randomise to re-inject current joystick position and re-run
inference before routing outputs, eliminating the jump on first
joystick move after randomise.
Defaults: tame=1, spread=0.6 across all app variants.
Faithful JS port of nisps-core MLP + IML engine with a touch-friendly
UI for exploring neural parameter mapping visually. Two learning modes:
example-based (set slider targets) and RL feedback (thumbs up/down with
exploration noise). Flow field particle system controlled by 8 MLP outputs.
