bluemsi/2nd
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: finalized wiki integrity maintenance (v3.0 standard) - pruned 1400+ stubs and fixed 11k+ ghost links

Browse Source
This commit is contained in:
Antigravity Agent
2026-05-02 09:18:34 +09:00
parent c84dcb8371
commit 6445fcc05b
13150 changed files with 55394 additions and 100862 deletions
Download Patch File Download Diff File Expand all files Collapse all files
10_Wiki/Topics_Blog/Probabilistic-Reasoning.md
+2 -2
View File
@@ -6,7 +6,7 @@ tags: [auto-reinforced, probabilistic-reasoning, probability, uncertainty, bayes
last_reinforced: 2026-04-20
---
# [[Probabilistic-Reasoning]]
# [[Probabilistic-Reasoning|Probabilistic-Reasoning]]
## 📌 한 줄 통찰 (The Karpathy Summary)
> "0 아니면 1이 아닌 세상을 읽는 법: '이것은 분명히 참이다'라고 단언하는 대신, '이것이 참일 확률은 80%다'라고 정의하며 새로운 정보가 들어올 때마다 그 확률을 끊임없이 업데이트해 나가는 유연한 지성."
@@ -26,6 +26,6 @@ last_reinforced: 2026-04-20
- **정책 변화(RL Update)**: 생성형 AI가 답변을 내놓는 과정 자체가 다음 단어가 뒤따라올 확률 정책을 계산하는 거대한 확률적 추론 정책이며, 이를 더 이성적으로 만들기 위해 '확률적 빔 서치'나 '최적 샘플링 정책' 등이 도입됨. (Large Language Models (LLM)와 연결)
## 🔗 지식 연결 (Graph)
- [[Logic]], [[MAP-Estimation]], [[Large Language Models (LLM)]], [[Inexact-Science]], [[Judgment]]
- [[Logic|Logic]], [[MAP-Estimation|MAP-Estimation]], [[Large Language Models (LLM)|Large Language Models (LLM)]], [[Inexact-Science|Inexact-Science]], [[Judgment|Judgment]]
- **Modern Tech/Tools**: Bayesian networks, Hidden Markov Models, Probabilistic programming (Pyro, PyMC3).
---