feat: complete wikification of War Commander batch 1&2 and final grey dot cleanup

2026-04-27 18:58:22 +09:00
parent 3424166ea2
commit 6b86b0da4c
2706 changed files with 9074 additions and 7273 deletions
@@ -1,6 +1,6 @@
 ---
 id: P-REINFORCE-AUTO-BACK-002
-category: "[[10_Wiki/💡 Topics/AI]]"
+category: "10_Wiki/💡 Topics/AI"
 confidence_score: 1.00
 tags: [auto-reinforced, backpropagation, deep-learning, machine-learning-foundations, calculus, neural-networks]
 last_reinforced: 2026-04-20
@@ -27,6 +27,6 @@ last_reinforced: 2026-04-20
 - **정책 변화(RL Update)**: 역전파 연산 효율을 극대화하기 위해 하드웨어(GPU/NPU) 수준에서 행렬 연산을 가속하는 정책이 수립되었고, 최근에는 역전파 없이 학습하는 생물학적 뇌 모델(Forward-Forward 등)에 대한 대안 정책 연구도 활발함.

 ## 🔗 지식 연결 (Graph)
- [[stochastic gradient descent]], [[Deep Learning]], [[Neural Networks]], [[Machine-Learning-Foundations]], [[Reward Prediction Error]]
+- [[stochastic gradient descent]], Deep Learning, Neural Networks, [[Machine-Learning-Foundations]], [[Reward Prediction Error]]
 - **Modern Tech/Tools**: PyTorch, TensorFlow, Autograd engines.
 ---