SirStone f70d9e6d1e refactor(SNNBot): replace reservoir with direct binary readout ...

Delete 1024-neuron reservoir — it added noise, not features.
Direct 80-bit input → 72 output bins via popcount + WTA Hebbian.
Same learning rule (OR reinforce, AND NOT punish), zero indirection.
Reservoir adds value for temporal features (step 3), not now.

2026-09-14 23:13:01 +02:00

..

research

research(SNNBot): survey existing lead-targeting and enemy tracking code

2026-09-13 20:30:10 +02:00

src

refactor(SNNBot): replace reservoir with direct binary readout

2026-09-14 23:13:01 +02:00

tests

feat(SNNBot): upgrade bot API, fix debug overlay and aiming lines

2026-09-13 10:24:20 +02:00

.gitignore

feat(SNNBot): upgrade bot API, fix debug overlay and aiming lines

2026-09-13 10:24:20 +02:00

config.nims

feat(SNNBot): upgrade bot API, fix debug overlay and aiming lines

2026-09-13 10:24:20 +02:00

SNNBot

feat(SNNBot): upgrade bot API, fix debug overlay and aiming lines

2026-09-13 10:24:20 +02:00

SNNBot_garage.json

feat(SNNBot): upgrade bot API, fix debug overlay and aiming lines

2026-09-13 10:24:20 +02:00

SNNBot_garage.sh

feat(SNNBot): upgrade bot API, fix debug overlay and aiming lines

2026-09-13 10:24:20 +02:00

SNNBot.nimble

feat(SNNBot): add STDP learner and integration test (#153, #155)

2026-09-13 10:31:07 +02:00