diff options
Diffstat (limited to 'docs')
| -rw-r--r-- | docs/CLAIM_LARGEST_NOBP.md | 6 |
1 files changed, 4 insertions, 2 deletions
diff --git a/docs/CLAIM_LARGEST_NOBP.md b/docs/CLAIM_LARGEST_NOBP.md index 8bb69e5..0edbc3a 100644 --- a/docs/CLAIM_LARGEST_NOBP.md +++ b/docs/CLAIM_LARGEST_NOBP.md @@ -60,8 +60,10 @@ top-1 33.81 vs BP 32.35 (top-5 13.23 vs 12.20) — **a real 1.0-1.5pp gap remain EP's inventor**. Their construction IS the layered-energy bridge (their Eq. 10 == our cascade energy; free phase == forward pass; single-equilibrium simplification == our single-sided legality; their mod-PGD/asynchronous traversal ~= our fb solver). Vision classification only; hardware explicitly -punted ("remains unclear whether F_PCN could be efficiently realized in hardware"). Parameter count -not stated (VGG10-class, plausibly 20-130M) => **"largest NN today" is CONTESTED — do not use.** +punted ("remains unclear whether F_PCN could be efficiently realized in hardware"). Parameter count (computed from their Table 6): conv ~9.2M + dense 25088x2048 ~51.4M + 2048x1000 ~2.0M += **~62.7M > our 42.75M** => **"largest NN today" is THEIRS — do not use.** Also measured: their +EP/BP wall-clock = 12x centered / 6.7x random (VGG10 ImageNet: 18d/10d vs BP 36h, single A100) vs +OUR 3.2x — the solver-efficiency differentiator, measured on both sides. RE-SCOPED claims that hold today: largest/first TRANSFORMER fully trained without BP; first AUTOREGRESSIVE LANGUAGE MODEL; the only zero-gap result (matched-tuning indistinguishability; their best retains 1.0-1.5pp). At 1B+ the unqualified largest-NN claim reactivates regardless of their |