Bandingkan metode
Tinjau metode pilihan Anda berdampingan; baris yang berbeda akan disorot.
| LoRA dan PEFT× | Variational Autoencoder× | Vision Transformer× | |
|---|---|---|---|
| Bidang | Pembelajaran Mendalam | Pembelajaran Mendalam | Pembelajaran Mendalam |
| Keluarga | Machine learning | Machine learning | Machine learning |
| Tahun asal≠ | 2022 | 2014 | 2021 |
| Pencetus≠ | Hu, E. J. et al.; Lester, B. et al. | Kingma, D. P. & Welling, M. | Dosovitskiy, A. et al. |
| Tipe≠ | Parameter-efficient fine-tuning of large pretrained models | Deep generative latent-variable model (encoder–decoder) | Transformer architecture for images (self-attention over patches) |
| Sumber perintis≠ | Hu, E. J. et al. (2022). LoRA: Low-Rank Adaptation of Large Language Models. ICLR. link ↗ | Kingma, D. P. & Welling, M. (2014). Auto-Encoding Variational Bayes. International Conference on Learning Representations (ICLR). link ↗ | Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR. link ↗ |
| Alias≠ | LoRA ve PEFT — Parametre Verimli İnce Ayar, Low-Rank Adaptation, parameter-efficient fine-tuning, prefix tuning | Değişkensel Otokodlayıcı (VAE), VAE, auto-encoding variational Bayes, deep latent variable model | Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images |
| Terkait | 5 | 5 | 5 |
| Ringkasan≠ | LoRA (Low-Rank Adaptation), introduced by Hu et al. in 2022, and the broader family of parameter-efficient fine-tuning (PEFT) methods adapt large pretrained language models to new tasks by training only a small number of extra parameters instead of every weight in the model. This makes fine-tuning possible with far less GPU memory and compute while leaving the original model largely untouched. | 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. | The Vision Transformer (ViT), introduced by Dosovitskiy and colleagues in 2021, splits an image into fixed-size patches, treats those patches as a sequence, and applies the Transformer self-attention mechanism to image classification. Given enough training data, it surpasses convolutional neural networks (CNNs). |
| ScholarGateSet data ↗ |
|
|
|