Bandingkan kaedah
Semak kaedah pilihan anda secara bersebelahan; baris yang berbeza akan diserlahkan.
| LSTM× | Pembelajaran Separa Selia× | Autoenkoder Variasi× | |
|---|---|---|---|
| Bidang≠ | Pembelajaran Mendalam | Pembelajaran Mesin | Pembelajaran Mendalam |
| Keluarga | Machine learning | Machine learning | Machine learning |
| Tahun asal≠ | 1997 | 1970s–2006 (formalized) | 2014 |
| Pengasas≠ | Hochreiter, S. & Schmidhuber, J. | Vapnik, V. N. and others (community of researchers, 1970s–2000s) | Kingma, D. P. & Welling, M. |
| Jenis≠ | Recurrent neural network (gated memory cell) | Learning paradigm | Deep generative latent-variable model (encoder–decoder) |
| Sumber perintis≠ | Hochreiter, S. & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780. DOI ↗ | Chapelle, O., Scholkopf, B., & Zien, A. (Eds.) (2006). Semi-Supervised Learning. MIT Press. ISBN: 978-0-262-03358-9 | Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR). link ↗ |
| Alias | LSTM (Uzun Kısa Dönem Bellek Ağı), long short-term memory, LSTM network, recurrent neural network with memory cells | SSL, semi-supervised machine learning, transductive learning, label-efficient learning | Değişkensel Otokodlayıcı (VAE), VAE, auto-encoding variational Bayes, deep latent variable model |
| Berkaitan | 5 | 5 | 5 |
| Ringkasan≠ | LSTM (Long Short-Term Memory) is a recurrent neural network architecture, introduced by Sepp Hochreiter and Jürgen Schmidhuber in 1997, that can learn long-term dependencies in sequential data and is widely used for time-series and sequence prediction. It keeps an internal memory that lets information persist across many time steps. | Semi-supervised learning (SSL) is a machine learning paradigm that trains models using a small set of labeled examples together with a much larger pool of unlabeled data. By leveraging the structure inherent in unlabeled data, SSL achieves accuracy closer to fully supervised models while requiring far fewer costly manual labels — making it practical when labeling is expensive, slow, or resource-constrained. | 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. |
| ScholarGateSet data ↗ |
|
|
|