diff options
Diffstat (limited to 'THREE_PART_EVIDENCE.md')
| -rw-r--r-- | THREE_PART_EVIDENCE.md | 89 |
1 files changed, 52 insertions, 37 deletions
diff --git a/THREE_PART_EVIDENCE.md b/THREE_PART_EVIDENCE.md index e3642e1..eef1477 100644 --- a/THREE_PART_EVIDENCE.md +++ b/THREE_PART_EVIDENCE.md @@ -5,7 +5,8 @@ Somato-dendritic innovation is a local correction for predictable teaching- channel error. It transfers across digital local learners, preserves coupled learning as the number of imperfect components grows, and can be implemented -with local sampling and subtraction in a hardware-realistic CLLN. +with local sampling and subtraction in a hardware-realistic Contrastive Local +Learning Network (CLLN). The method remains: @@ -26,16 +27,15 @@ learning rule without replacing that rule. |:--|:--|--:|--:|--:|--:|:--| | Dual Propagation | CIFAR-10 miniCNN, 5 seeds | 82.86% | 9.40% | — | 82.92% | Passed frozen confirmation | | Equilibrium Propagation | FashionMNIST ConvHopfield, 5 seeds | 76.26% | 31.38% | 67.90% | 74.52% | SDIL beats raw in every seed; strict gate failed because one seed favors calibration | -| Digital coupled learning | released ring tasks, size ladder pilot | reported by size | 37.5–62.5% error | 2.5–30.0% error | 0–7.5% error | Full confirmation running | -| Overclamped coupled learning | released ring tasks, size ladder pilot | 0–2.5% error | 25–50% error | — | 0–2.5% error | Clean-only time constant selected before biased endpoints | +| Digital coupled learning | 32-edge ring tasks, 40 tasks × 3 draws | 100.00% | 65.31% | 93.85% | 100.00% | Passed frozen confirmation | +| Overclamped coupled learning | 32-edge ring tasks, 40 tasks × 3 draws | 91.88% | 66.88% | — | 91.98% | Passed frozen confirmation | Sources: - `results/contrastive_bias/c1_gate.json` - `results/ep_bias/c1_gate.json` -- `results/coupled_ladder/p1_imperfection_pilot.json` -- `results/coupled_ladder/p1_bias_baseline_pilot.json` -- `results/coupled_ladder/p1_overclamp_selected_pilot.json` +- `results/coupled_ladder/p2_confirm_side4.json` +- `results/coupled_ladder/p3_overclamp_side4.json` The Dual Propagation result establishes strong transfer. The EP result shows transfer with a visible remaining clean gap and seed variance. Coupled learning @@ -48,34 +48,44 @@ The periodic grid ladder uses side lengths `4, 8, 12, 16, 24, 32`, or 32 to initial gate field, and component draw. Size-dependent update exposure is selected from ideal coupled learning only. -Pilot final classification error: +Confirmed final classification error: | Edges | Clean | Same-RMS noise | Raw | Static calibration | SDIL | |--:|--:|--:|--:|--:|--:| -| 32 | 0.0% | 0.0% | 50.0% | 2.5% | 0.0% | -| 128 | 0.0% | 0.0% | 62.5% | 2.5% | 0.0% | -| 288 | 2.5% | 5.0% | 52.5% | 2.5% | 2.5% | -| 512 | 2.5% | 10.0% | 47.5% | 5.0% | 2.5% | -| 1,152 | 2.5% | 17.5% | 50.0% | 10.0% | 7.5% | -| 2,048 | 2.5% | 22.5% | 37.5% | 30.0% | 2.5% | - -The raw learner has a large error floor at every size. Static calibration works -on small grids and degrades on larger grids. Relative to static calibration, -SDIL reduces the pilot excess-error growth slope by 88.1%; the paired -task-bootstrap slope-difference interval is positive. At 2,048 edges, SDIL -closes the full raw-to-clean final-error gap and reaches stable zero error on -80% of task runs, versus 0% for raw and static calibration. - -The tuned overclamp pilot gives the same structural result. Clean overclamping -ends at 0–2.5% error across the ladder. Imperfect overclamping ends at 25–50%, -while overclamping plus SDIL ends at 0–2.5%. SDIL therefore combines with the -strong-clamp correction. +| 32 | 0.00% | 0.73% | 34.69% | 6.15% | 0.00% | +| 128 | 1.25% | 2.60% | 37.92% | 6.46% | 1.25% | +| 288 | 1.88% | 8.02% | 48.12% | 6.35% | 1.88% | +| 512 | 2.50% | 11.35% | 47.71% | 9.58% | 2.50% | +| 1,152 | 2.50% | 19.38% | 48.44% | 18.13% | 2.92% | +| 2,048 | 1.56% | 26.67% | 49.90% | 27.19% | 2.29% | + +The raw learner has a large error floor at every size. Same-RMS noise and +static calibration both degrade as the grid grows. Relative to static +calibration, SDIL reduces the excess final-error growth slope by 96.2% (paired +task-bootstrap 95% interval 93.0% to 98.5%) and the excess stable-failure +growth slope by 89.5% (74.8% to 96.6%). Its excess error-AUC slope is slightly +negative, eliminating the corresponding positive static-calibration slope. +At 2,048 edges, SDIL closes 98.5% of the raw-to-clean final-error gap and +reaches stable zero error on 82.5% of trials, versus 0% for raw, 23.3% for +static calibration, and 87.5% for clean. + +The improvement has a measurement cost. At 2,048 edges SDIL uses 3,487 local +updates to the censored stable-zero target on average, versus 4,548 for static +calibration. Counting task and neutral edge measurements, SDIL uses 14.28 +million local scalar reads versus 9.35 million for static calibration, a +1.53-times ratio. Runs that miss stable zero receive the frozen 600-epoch +horizon in both cost summaries. + +The overclamp confirmation is complete through 1,152 edges. At that size, +clean overclamping, imperfect overclamping, and overclamping plus SDIL end at +1.25%, 45.31%, and 1.25% error. The 2,048-edge endpoint is still running. The publication figure and data are: -- `results/figs/figure_clln_scaling_pilot.pdf` -- `results/coupled_ladder/p1_scaling_analysis.json` -- `results/coupled_ladder/p1_scaling_source.csv` +- `results/figs/figure_clln_scaling_confirmation.pdf` +- `results/figs/figure_clln_scaling_confirmation_resources.pdf` +- `results/coupled_ladder/p2_scaling_analysis.json` +- `results/coupled_ladder/p2_scaling_source.csv` The mechanism statement is now explicit in `THEORY.md`. For a local state-dependent component error, conditional subtraction removes at least as @@ -85,9 +95,9 @@ produces an exact displaced optimum with excess objective `0.5 * delta^T H^+ delta`; the classification ladder tests whether this local effect reaches the downstream task endpoint. -The pilot has five task clusters and one component draw per task and size. The -running confirmation contains all 40 released tasks, three new component draws, -six sizes, and five core methods: 3,600 training trajectories. Its outputs are +The confirmation contains all 40 released tasks, three new component draws, +six sizes, and five core methods: 3,600 completed training trajectories. Its +outputs are `results/coupled_ladder/p2_confirm_side{4,8,12,16,24,32}.json`. ## Part 3: hardware-realistic simulation @@ -96,6 +106,12 @@ This part uses the nonlinear conductance law, periodic 4-by-4 topology, released Figure-5 tasks and initial gates, Appendix-C component imperfections, and explicit local voltage-square updates. +A descriptive reanalysis of released physical drift traces first checks the +problem assumption. Per-edge local affine bias reduces held-out RMSE to 0.21 +and 0.54 of a constant-bias model in the two released task pairs. This shows a +measured state-dependent component; it does not show SDIL training on +fabricated hardware. + The untouched confirmation uses 40 tasks and three new component draws, or 120 trials per method: @@ -126,6 +142,8 @@ Sources: - `results/physical_bias/p8_spice_autozero_primitive.json` - `results/figs/figure_physical_hardware_evidence_confirmation.pdf` - `results/physical_bias/p12_hardware_evidence_analysis.json` +- `results/physical_bias/p0_state_dependence.json` +- `results/figs/physical_bias_state_dependence.png` The hardware claim is: the full update is simulated with published device equations and nonideal local sampling, and its primitive sample/subtract path @@ -143,9 +161,6 @@ has a SPICE check. A fabricated-chip demonstration remains future work. ## Remaining gates -1. Complete and audit the 3,600-trajectory digital ladder confirmation. -2. Run the selected overclamp pair on the full task/device confirmation panel. -3. Rebuild the digital transfer and scaling figures from confirmation data; - the hardware-realistic figure is complete. -4. Audit every manuscript number - against its source JSON. +1. Finish the 2,048-edge overclamp endpoint and rebuild its scaling figure. +2. Finish the frozen 256-observation static-calibration stress test. +3. Audit every manuscript number against its source JSON. |