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

[G1-Sync] Manual knowledge update

Browse Source
This commit is contained in:
Antigravity Agent
2026-04-30 22:42:02 +09:00
parent 0bd4f19e38
commit c36c0644a1
4888 changed files with 18470 additions and 18602 deletions
Download Patch File Download Diff File Expand all files Collapse all files
10_Wiki/Topics/Dense vs Sparse Neural Networks.md
+3 -3
View File
@@ -1,8 +1,8 @@
---
id: P-REINFORCE-AI-DENSE-SPARSE
id: [[P-Reinforce]]-AI-DENSE-SPARSE
category: "10_Wiki/💡 Topics/AI"
confidence_score: 0.98
tags: [Neural Networks, Dense, Sparse, MoE, Efficiency]
tags: [Neural Networks, Dense, Sparse, MoE, [[Efficiency]]]
last_reinforced: 2026-04-20
---
@@ -23,5 +23,5 @@ last_reinforced: 2026-04-20
- 희소 행렬 연산은 하드웨어(GPU) 가속기에서 효율적으로 처리하기가 까다로운 면이 있다. 따라서 소프트웨어적인 '희소화'와 하드웨어의 '가속 효율' 사이의 균형점을 찾는 것이 현대 AI 공학의 최대 화두다.
## 🔗 지식 연결 (Graph)
- Related: Differentiable-Programming , Deep-Reinforcement-Learning
- Related: Differentiable-Programming , Deep-[[Reinforcement-Learning]]
- Foundation: [[Information Theory]]