Compara mètodes

Revisa els mètodes seleccionats l'un al costat de l'altre; les files que difereixen es ressalten.

Xarxa Neuronal Convolucional (Classificació)×Autoencoder×
CampAprenentatge profundAprenentatge profund
FamíliaMachine learningMachine learning
Any d'origen19982006
Autor originalLeCun, Y. et al.Hinton, G.E. & Salakhutdinov, R.R.
TipusDeep neural network (convolutional)Neural network (encoder-decoder)
Font seminalLeCun, Y., Bottou, L., Bengio, Y. & Haffner, P. (1998). Gradient-Based Learning Applied to Document Recognition. Proceedings of the IEEE, 86(11), 2278–2324. DOI ↗Hinton, G.E. & Salakhutdinov, R.R. (2006). Reducing the Dimensionality of Data with Neural Networks. Science, 313(5786), 504–507. DOI ↗
ÀliesCNN (Evrişimli Sinir Ağı — Sınıflandırma), CNN classification, ConvNet, convolutional network classifierOtokodlayıcı (Autoencoder), otokodlayıcı, auto-encoder, encoder-decoder network
Relacionats54
ResumA Convolutional Neural Network (CNN) is a deep learning model, established by LeCun and colleagues in 1998, that learns local patterns directly from images and structured data to classify them. Stacks of convolutional filters discover increasingly abstract features, so manual feature engineering can be largely reduced.An autoencoder is an encoder-decoder neural network, popularised by Hinton and Salakhutdinov in 2006, that compresses data into a low-dimensional latent code and then reconstructs it, enabling dimensionality reduction and anomaly detection. By learning to rebuild its own input through a narrow bottleneck, it discovers a compact representation of the data.
ScholarGateConjunt de dades
  1. v1
  2. 1 Fonts
  3. PUBLISHED
  1. v1
  2. 1 Fonts
  3. PUBLISHED

Ves a la cerca Download slides

ScholarGateCompara mètodes: Convolutional Neural Network · Autoencoder. Recuperat el 2026-06-15 de https://scholargate.app/ca/compare