SirStone/SirRoboGarage
1
0
Fork 0
Code Issues 28 Pull Requests Actions Projects Releases Wiki Activity

docs: correct counted-SBC decay amortised cost figure

Browse Source
This commit is contained in:
Davide Cappellini
2026-09-25 08:43:48 +02:00
parent d85ff53d34
commit 4270136948
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/bitbrain_counted_sbc.md
+3 -3
View File
@@ -61,7 +61,7 @@ alternatives for three reasons:
The bitset `infer` is unchanged. The bitset `infer` is unchanged.
**Config (which is which).** The default is and remains `smBitset`; the bitset **Config (which is which).** The default is and remains `smBitset`; the bitset
path is byte-for-byte unchanged. Counted mode is selected explicitly or at path's behaviour is exactly unchanged. Counted mode is selected explicitly or at
runtime: runtime:
| knob | kind | values | | knob | kind | values |
@@ -92,8 +92,8 @@ The gun-sized byte-per-cell cost is 12 MiB — acceptable for a gun (and the
whole 12.1 MiB model fits comfortably next to the rest of a bot). The MNIST whole 12.1 MiB model fits comfortably next to the rest of a bot). The MNIST
240 MiB is fine for an offline measurement machine but is 8× the bit tensor; 240 MiB is fine for an offline measurement machine but is 8× the bit tensor;
packed 4-bit (INFERRED, not implemented) would halve both figures. At packed 4-bit (INFERRED, not implemented) would halve both figures. At
MNIST scale, `decayEvery = 2000` costs ≈ 0.2 ms/learn amortised (measured train MNIST scale, `decayEvery = 2000` costs ≈ 0.07–0.08 ms/learn amortised (measured
30.3 s vs 25.4 s over 60k for the decay arm, i.e. ~0.08 ms/sample extra). train 28–30 s vs 24–25 s over 60k for the decay arm).
--- ---