Порівняння методів
Переглядайте обрані методи поруч; рядки з відмінностями підсвічено.
| Напівкерована LSTM× | Варіаційний автокодувальник× | |
|---|---|---|
| Галузь | Глибоке навчання | Глибоке навчання |
| Родина | Machine learning | Machine learning |
| Рік появи≠ | 2015–2018 | 2014 |
| Автор методу≠ | Hochreiter, S. & Schmidhuber, J. (LSTM); semi-supervised extensions by various authors (2015–2020) | Kingma, D. P. & Welling, M. |
| Тип≠ | Semi-supervised sequence model | Deep generative latent-variable model (encoder–decoder) |
| Основоположне джерело≠ | Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780. DOI ↗ | Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR). link ↗ |
| Інші назви | SSL-LSTM, semi-supervised sequence model, LSTM with unlabeled data, pseudo-label LSTM | Değişkensel Otokodlayıcı (VAE), VAE, auto-encoding variational Bayes, deep latent variable model |
| Пов'язані≠ | 3 | 5 |
| Підсумок≠ | Semi-supervised LSTM combines the sequential memory of Long Short-Term Memory networks with semi-supervised learning strategies — using a small labeled dataset alongside a large pool of unlabeled sequences. The model is pretrained or regularized on unlabeled data, then fine-tuned on labeled examples, delivering strong generalization when labeled data is scarce. | The Variational Autoencoder (VAE) is a deep generative latent-variable model, introduced by Diederik Kingma and Max Welling in 2014, that encodes data as a probability distribution in a latent space and samples from that distribution to generate new examples. It is used for data generation, anomaly detection, and feature learning. |
| ScholarGateНабір даних ↗ |
|
|