ScholarGate
Асистент

Сравнение на методи

Прегледайте избраните методи един до друг; редовете с разлики са откроени.

Колмогоров-Арнолд мрежи×Vision Transformer×
ОбластДълбоко обучениеДълбоко обучение
СемействоMachine learningMachine learning
Година на възникване20242021
СъздателZiming LiuDosovitskiy, A. et al.
ТипNeural network architectureTransformer architecture for images (self-attention over patches)
Основополагащ източникLiu, Z., Wang, Y., Vaidya, S., Ruehle, F., Halverson, J., Soljačić, M., Hou, T. Y., & Tegmark, M. (2024). KAN: Kolmogorov-Arnold Networks. arXiv preprint arXiv:2404.19756. link ↗Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR. link ↗
Други названияKAN, Kolmogorov-ArnoldGörsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Свързани45
РезюмеKolmogorov-Arnold Networks (KAN) is a neural network architecture introduced by Liu et al. in 2024 that replaces linear transformations with learned univariate functions on edges. Inspired by the Kolmogorov-Arnold representation theorem, KAN achieves superior function approximation with fewer parameters than traditional MLPs, offering potential efficiency gains and improved interpretability.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).
ScholarGateНабор от данни
  1. v1
  2. 1 Източници
  3. PUBLISHED
  1. v1
  2. 2 Източници
  3. PUBLISHED

Към търсенето Изтегляне на слайдове

ScholarGateСравнение на методи: Kolmogorov-Arnold Networks · Vision Transformer. Извлечено на 2026-06-19 от https://scholargate.app/bg/compare