ScholarGate
어시스턴트

방법 비교

선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.

지식 증류×서포트 벡터 머신 (분류)×
분야딥러닝머신러닝
계열Machine learningMachine learning
기원 연도20151995
창시자Hinton, G., Vinyals, O. & Dean, J.Cortes, C. & Vapnik, V.
유형Neural network compression (teacher–student)Maximum-margin classifier (kernel method)
원전Hinton, G., Vinyals, O. & Dean, J. (2015). Distilling the Knowledge in a Neural Network. NeurIPS Deep Learning Workshop. link ↗Cortes, C. & Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20, 273–297. DOI ↗
별칭Bilgi Damıtma (Knowledge Distillation), bilgi damıtma, teacher-student distillation, model distillationDestek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier
관련55
요약Knowledge Distillation is a model-compression technique, introduced by Geoffrey Hinton and colleagues in 2015, that trains a small student model using the soft-label outputs of a large teacher model. Distilled models such as DistilBERT and TinyBERT reach roughly 97% of the larger model's performance while running far faster.The Support Vector Machine, introduced by Corinna Cortes and Vladimir Vapnik in 1995, is a classifier that finds the optimal separating hyperplane between classes in a high-dimensional space. It chooses the boundary that leaves the widest possible margin to the nearest training points, which makes its decisions robust on new data.
ScholarGate데이터셋
  1. v1
  2. 2 출처
  3. PUBLISHED
  1. v1
  2. 1 출처
  3. PUBLISHED

검색으로 이동 슬라이드 다운로드

ScholarGate방법 비교: Knowledge Distillation · Support Vector Machine. 2026-06-19에 다음에서 검색함: https://scholargate.app/ko/compare