2nd/10_Wiki/Topics/AI_and_ML/Non-linear-Activation-Functions.md

id, title, category, status, canonical_id, aliases, duplicate_of, source_trust_level, confidence_score, verification_status, tags, raw_sources, last_reinforced, github_commit, tech_stack

id	title	category	status	canonical_id	aliases	duplicate_of	source_trust_level	confidence_score	verification_status	tags	raw_sources	last_reinforced	github_commit	tech_stack
wiki-2026-0508-non-linear-activation-functions	Non-linear Activation Functions	10_Wiki/Topics	duplicate	Leaky-ReLU-and-Activations	Activation Functions Nonlinearities ReLU Family	Leaky-ReLU-and-Activations	A	0.9	redirected	redirect activation relu gelu swish		2026-05-10	pending	language framework Python PyTorch

REDIRECT → Leaky-ReLU-and-Activations

이 문서는 Leaky-ReLU-and-Activations 로 통합되었다. ReLU/LeakyReLU/PReLU/ELU/GELU/SiLU(Swish)/Mish/SwiGLU 등 비선형 활성화 함수 전반은 정식 문서를 참고하라.

요약

• 비선형성이 신경망 표현력의 핵심.
• 2026 표준: Transformer는 GELU/SwiGLU, CNN은 SiLU/Mish, classic은 ReLU 변형.

🔗 Graph

• 부모: Leaky-ReLU-and-Activations (canonical)
• 인접: Neural Networks, Backpropagation, Vanishing Gradient

🕓 Changelog

• 2026-05-08 Phase 1 자동 생성
• 2026-05-10 Manual cleanup — REDIRECT 처리, 정식 문서로 통합