방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 준지도형 다층 퍼셉트론× | 준지도학습 합성곱 신경망× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2006–2013 | 2013–2017 |
| 창시자≠ | Chapelle, O.; Scholkopf, B.; Zien, A. (eds.); Lee, D.-H. | Lee, D.-H.; Tarvainen, A. & Valpola, H. (among others) |
| 유형≠ | Semi-supervised feedforward neural network | Semi-supervised deep learning |
| 원전≠ | Chapelle, O., Scholkopf, B. & Zien, A. (Eds.) (2006). Semi-Supervised Learning. MIT Press. ISBN: 978-0-262-03358-9 | Lee, D.-H. (2013). Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. ICML Workshop on Challenges in Representation Learning. link ↗ |
| 별칭 | SSL-MLP, semi-supervised MLP, semi-supervised feedforward network, partially supervised multilayer perceptron | SSL-CNN, semi-supervised CNN, self-training CNN, pseudo-label CNN |
| 관련≠ | 4 | 5 |
| 요약≠ | A semi-supervised multilayer perceptron (SSL-MLP) is a feedforward neural network trained on a small pool of labeled examples together with a larger pool of unlabeled examples. By combining supervised cross-entropy loss on labeled data with an unsupervised consistency or pseudo-label objective on unlabeled data, it extracts far more signal from the data than a purely supervised MLP trained on labels alone. | A Semi-supervised CNN trains a convolutional network on a small labeled image set and a larger pool of unlabeled images simultaneously, using techniques such as pseudo-labeling and consistency regularization to extract supervisory signal from unlabeled data. This strategy closes much of the performance gap caused by scarce annotations without requiring additional human labeling effort. |
| ScholarGate데이터셋 ↗ |
|
|