예측 모델링에 대한 실용서
Source
Evernote/IFTTT Feedly/예측 모델링에 대한 실용서.md
Summary
R 언어의 예측 모델링 패키지인 caret을 소개하며, Max Kuhn 박사의 경험과 철학을 높게 평가한다. 특히 10-fold 교차검증을 멀티코어로 실행하여 최적 파라미터를 찾는 모델 평가 방식에 주목한다.
Key Points
- R 커뮤니티에서
caret패키지가 예측 모델링 실무에 유용함 - Max Kuhn 박사의
caret관련 튜토리얼 및 철학에 대한 긍정적 평가 - 10-fold 교차검증과 멀티코어 연산을 통한 최적 파라미터 탐색 강조
Related
-
Enlisting the Ghost: Modeling Empty Categories for Machine Translation
-
Improved Domain Adaptation for Statistical Machine Translation
-
Scalable Decipherment for Machine Translation via Hash Sampling
-
Social Event Classification via Boosted Multimodal Supervised Latent Dirichlet Allocation
-
Feature Ensemble Plus Sample Selection: Domain Adaptation for Sentiment Classification
-
Active Learning through Adaptive Heterogeneous Ensembling (AHE)
-
An Unsupervised Feature Selection Framework for Social Media Data
-
Speech and Natural Language: Where Are We Now And Where Are We Headed
-
Accurate and Compact Large Vocabulary Speech Recognition on Mobile Devices
-
Knowledge-Based Approaches to Information Management in Coalition Environments
-
Efficient Estimation of Word Representations in Vector Space
-
Knowledge-Based Approaches to Information Management in Coalition Environments
-
Coordinated Multi-Device Presentations: Ambient-Audio Identification
-
Web Service Compositions with Fuzzy Preferences: A Graded Dominance Relationship-Based Approach