diff options
Diffstat (limited to 'index.html')
| -rw-r--r-- | index.html | 4 |
1 files changed, 2 insertions, 2 deletions
@@ -198,7 +198,7 @@ <li><b>Verified gradient fidelity:</b> the EP update maintains cosine ≈0.99 to the true backprop gradient throughout training: measured, at scale. Larger non-backprop transformers in the literature train most parameters with <i>local backprop inside blocks</i>; ours use none.</li> - <li><b>Hardware-ready by measurement, not assumption:</b> 8-bit quantization shows no EP-specific + <li><b>Hardware compatible, with measurements to show it:</b> 8-bit quantization shows no EP-specific penalty against an equally-quantized backprop twin; under injected analog faults (1% forward noise, 10% error-channel noise, device-tolerance mismatch) the EP estimator tracks the faulted network at cosine ≈0.97: learning co-adapts to the hardware.</li> @@ -302,7 +302,7 @@ <h2 class="title is-3">Roadmap</h2> <div class="content has-text-justified"> <p>Staged scaling with matched BP controls and hardware-relevant ablations at every rung: a 150M-600M - ladder (does the gap grow or shrink with scale: measured, not assumed), then 1B-3B; each stage + ladder (the gap is measured against a backprop twin at every rung), then 1B-3B; each stage gated on the previous stage’s loss, alignment, and throughput numbers. In parallel: the algorithm→regime map across the activity-difference family (contrastive / coupled-learning arms on the same harness), and a bounded single-column hardware feasibility study.</p> |