This website requires JavaScript.
Explore
Guide
MQL5
AlgoBook
Freelance
Forum
Help
Register
Sign in
English
Bahasa Indonesia
Dansk
Deutsch
English
Español
Esperanto
Filipino
Français
Italiano
Latviešu
Magyar nyelv
Nederlands
Plattdüütsch
Polski
Português de Portugal
Português do Brasil
Slovenščina
Suomi
Svenska
Türkçe
Čeština
Ελληνικά
Български
Русский
Українська
فارسی
日本語
简体中文
繁體中文(台灣)
繁體中文(香港)
한국어
Rixa2020
/
Warrior_EA
Watch
1
Star
0
Fork
You've already forked Warrior_EA
0
forked from
MrBaro75/Warrior_EA
Code
Pull requests
Activity
main
Warrior_EA
/
cpu_directml.log
218 lines
102 KiB
Text
Raw
Permalink
Normal View
History
Unescape
Escape
feat(opencl): add feedback alignment support to weight update kernels Introduce an `optimizer` parameter to UpdateWeightsMomentum, UpdateWeightsConvMomentum, and UpdateWeightsAdam kernels. When set to a non-zero value, the gradient used for weight updates is multiplied by ±1 based on the parity of the weight index, implementing a basic feedback alignment signal for experimentation. When zero, the standard gradient is used unchanged. This allows A/B testing of alternative learning signals without modifying the rest of the training pipeline.
2026-07-28 15:01:40 -04:00
<EFBFBD>
<EFBFBD>
G