monkey-w1n5t0n
|
22efb1c411
|
feat(nisps/ml): crystallise Explore-and-place into shared FeedbackController
Add FeedbackMode::ExploreAndPlace + Idle/Exploring/Placing state machine
(no-heap, deterministic nisps::Rng): enter/exit_explore, reroll, nudge, undo,
begin_place, commit_place, cancel_place + on_down/on_up browser policy. Wire
the nisps_ml_feedback_* C API + EXPORTED_FUNCTIONS, extend parity Stage 5d.
Fix set_mode(3) falling back to Avoid. Native ctest 4/4; parity native==WASM
within 1e-5 (max delta 2.4e-7). Rebuilt nisps.{js,wasm}.
|
2026-06-28 04:14:12 +02:00 |
|
w1n5t0n
|
825ed6ad33
|
feat(nisps/ml): MLP library with fixed-architecture template + spread-aware RL (meml-wmh)
Stream 2 of the clean-slate rewrite: nisps/ml/ replaces src/memlp/ with a
header-only, heap-free MLP that satisfies nisps::core::MLEngine.
Files (nisps/ml/):
- activations.hpp — ReLU (leaky 0.01 for parity), sigmoid, tanh
- loss.hpp — MSE per-sample (fixes meml-ues double-scaling: returns the
sample's MSE without an extra 1/N multiplication; the training loop
averages explicitly)
- init.hpp — uniform/Xavier/spread-aware weight init
- training.hpp — gradient clip helper (±10.0 matches legacy)
- rl.hpp — move_weights with per-layer Xavier scaling, weight decay
(10% * spread), gaussian noise via the deterministic Rng (matches the
legacy JS sum-of-three-uniforms shape); draw_weights also spread-aware
- stats.hpp — per-layer mean/max/dead/saturating diagnostics
- mlp.hpp — 4-layer (3 hidden + sigmoid output) MLP class with
std::array-backed weights, biases, gradient accumulators, dataset
ring buffer (default 128 examples), loss history (default 4096 iters).
Bias is a separate per-layer parameter — no input-vector mutation.
Flat get_weights/set_weights layout: weights all layers (row-major,
layer order), then biases all layers.
Tests (tests/cpp/, all 50 passing under -Wall -Wextra -Werror -Wpedantic):
- test_mlp_init.cpp — deterministic seeding, spread regimes,
static_assert MLEngine concept satisfied
- test_mlp_inference.cpp — golden hand-computed forward pass match,
sigmoid output range, set_input bounds
- test_mlp_training.cpp — XOR convergence (loss < 0.01 in <2k iters),
ring-buffer eviction
- test_mlp_loss.cpp — meml-ues regression test: reported loss equals
hand-computed average MSE without extra 1/N scaling; sample weights
honoured
- test_mlp_rl.cpp — move_weights respects output_pin_mask (final-layer
rows + biases preserved); spread regimes; grad clear after draw_weights
- test_mlp_serialize.cpp — get_weights/set_weights round-trip preserves
inference exactly; eval_loss is non-mutating; infer_batch matches
individual inference
Verification:
- Clean build, no warnings
- 50 tests pass (22 prior + 28 new)
- No std::vector / new / malloc in nisps/ml/
- All float literals .f-suffixed in code (comments excepted)
|
2026-04-29 15:55:43 +03:00 |
|