No description
9490e20a7a
Geometric dislike (rl-feedback-design §2.1/§4; upstream InterfaceRL @
0a541cc ported verbatim, constants included):
- nisps/ml/replay.hpp: ReplayView over storage-owned buffers — deepen-or-
store negatives (dedup 0.05, clamp -16), k-NN positive centroid with
deterministic index tie-break + fixed accumulation order, proportional
decay (0.0025*max(|r|,1)) + eviction, order-preserving compaction.
- nisps/ml/geo_push.hpp: push-away target (pushStep clamp(|avgNeg|,.25,1)
*0.5, taper /(1+len), useRandom on len<=1e-4 via nisps::Rng — the single
deliberate divergence from libc rand()), negLRRatio 0.5-0.4*negFraction.
- mlp.hpp: train_targets(input, computed-target, lr, out_mask) — trains
toward computed targets (negative lr = cold-start train-away); solo/
focus gating zeroes masked derivs.
- feedback.hpp: AvoidStyle {Geometric (new default), Diffuse (legacy
move_weights, kept for A/B)}; dislike_geometric() collapses upstream's
press+optimise into one synchronous call; on_up in geometric Avoid
feeds the positive centroid; dislike-multiplier bookkeeping. Storage
gains replay buffers (Fixed: ReplayCap=32 firmware default ≈ +8KB SRAM;
Dynamic arena: cap 64).
- bindings: nisps_ml_feedback_{dislike_geometric,store_positive,
positive_count,negative_count,set_avoid_style} + P3.2 jolt/OU ABI:
nisps_ml_jolt_{press,step,release,active,lr_scale,tick_lr_ramp},
nisps_ml_explore_{intensity,get_intensity,apply} (OUNoise<4096>
over-provisioned; same code the firmware ModeBase runs).
- parity v4: Stage 6 scripted geometric session (2 likes → 2 dislikes,
f32-exact heard vectors via Math.fround) — 961 floats PASS at 2.4e-7.
- tests: test_mlp_geo_dislike.cpp (replay dedup/deepen/clamp, centroid
tie-break, push direction/taper/mask/clamp, cold-start inertness +
train-away, determinism, Diffuse legacy); legacy Avoid test pinned to
Diffuse per the ADR's deliberate-break note.
Firmware: PAFSynth .text/.data unchanged (geometric path not referenced
by current glue). NOTE: discovered pre-existing bug 10c3e55c — the
explore/place wiring is linker-GC'd out of the PAFSynth ELF (predates
this refactor; evidence in the ergo task).
|
||
|---|---|---|
| .claude/worktrees/agent-ae87fe47/playground/js/shapeseq | ||
| .github/workflows | ||
| .vscode | ||
| assets/media | ||
| codegen | ||
| data | ||
| docs | ||
| firmware | ||
| manifold | ||
| nisps | ||
| playground/dist | ||
| schemas | ||
| scripts | ||
| src | ||
| tests | ||
| vcv | ||
| .envrc | ||
| .gitignore | ||
| .gitmodules | ||
| AGENTS.md | ||
| ALIGNMENT.md | ||
| CLAUDE.md | ||
| LICENSE | ||
| MAP.md | ||
| NISPS_CORE_EXTRACTION_PLAN.md | ||
| NISPS_CORE_TASKS.md | ||
| package-lock.json | ||
| package.json | ||
| playwright.config.js | ||
| README.md | ||
| synth-midi-cc.json | ||
Neural Interactive Shaping of Parameter Spaces
https://musicallyembodiedml.github.io/memlnaut/approaches/nisps
Firmware
The hardware firmware targets the MEMLNaut RP2350 build and uses repo-local helper scripts for the known-good build configuration:
git submodule update --init --recursive
scripts/build-firmware.sh
scripts/flash-firmware.sh
scripts/build-and-flash-firmware.sh
Notes:
- The scripts build for
rp2040:rp2040:solderparty_rp2350_stamp_xlwithOptimize3. - The build forces C++20 because the firmware uses
std::spanand concepts. build-firmware.shaccepts an optional variant name such asMEMLCeliumorBreakOr. Matching remains case-insensitive, somemlceliumstill works. If you omit it in an interactive shell, the script parsesMEMLNaut-NISPS.ino, prompts for a variant, and rewrites the activeMEMLNAUT_MODE_TYPEbefore building.flash-firmware.shaccepts an optional mountpoint argument, or auto-detects common UF2 bootloader mounts such as/run/media/$USER/RP2350and/run/media/$USER/RPI-RP2.
Manifold (browser app)
Try NISPS in your browser — no hardware required. Manifold is the React front-end running the same C++ engines + ML as the firmware, compiled to WASM:
cd manifold
bun install
bun run dev
Staging deployment: https://meml.lnfinitemonkeys.org/next/
Train a neural network to map input gestures to synth parameters through interactive machine learning: place examples, or use verdict-based feedback (explore-and-place, geometric dislike).
(The former SolidJS playground was retired in July 2026 — archived on branch
archive/playground-solidjs, tag playground-solidjs-final.)