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/Zero Shot and Few Shot Learning.md
+2 -2
View File
@@ -6,7 +6,7 @@ tags: [auto-reinforced, few-shot, zero-shot, in-context-learning, prompting, llm
last_reinforced: 2026-04-20
---
# [[Zero Shot and Few Shot Learning]]
# [[Zero Shot and Few Shot Learning|Zero Shot and Few Shot Learning]]
## 📌 한 줄 통찰 (The Karpathy Summary)
> "예시가 있느냐 없느냐의 차이: 추가 학습 없이 명령어만으로 문제를 푸는 '생지능(Zero Shot)'과, 두세 개의 힌트를 주어 모델의 방향성을 잡아주는 '힌트 학습(Few Shot)'을 통해 AI의 범용성을 극대화하는 기법."
@@ -29,6 +29,6 @@ last_reinforced: 2026-04-20
- **정책 변화(RL Update)**: 데이터 개인정보 보호 정책이 강화됨에 따라, 데이터를 모델에 주입해 학습시키지 않고 프롬프트 수준에서만 활용하여 휘발시키는 '프라이버시 친화적 제로샷 추론 정책'이 기업용 AI 활용의 표준이 됨.
## 🔗 지식 연결 (Graph)
- Foundational Models, [[Prompt-Engineering]], [[Transfer Learning]], [[SFT (Supervised Fine-Tuning)]], NLP (자연어 처리)
- Foundational Models, [[Prompt-Engineering|Prompt-Engineering]], [[Transfer Learning|Transfer Learning]], [[SFT (Supervised Fine-Tuning)|SFT (Supervised Fine-Tuning)]], NLP (자연어 처리)
- **Modern Tech/Tools**: LangChain prompt templates, Meta Llama-3 few-shot benchmarks.
---