Σύγκριση μεθόδων

	Συνελικτικό Νευρωνικό Δίκτυο (Ταξινόμηση)	Αυτοκωδικοποιητής	Μηχανή Υποστήριξης Διανυσμάτων (Ταξινόμηση)
Πεδίο	Βαθιά Μάθηση	Βαθιά Μάθηση	Μηχανική Μάθηση
Οικογένεια	Machine learning	Machine learning	Machine learning
Έτος προέλευσης	1998	2006	1995
Δημιουργός	LeCun, Y. et al.	Hinton, G.E. & Salakhutdinov, R.R.	Cortes, C. & Vapnik, V.
Τύπος	Deep neural network (convolutional)	Neural network (encoder-decoder)	Maximum-margin classifier (kernel method)
Θεμελιώδης πηγή	LeCun, Y., Bottou, L., Bengio, Y. & Haffner, P. (1998). Gradient-Based Learning Applied to Document Recognition. Proceedings of the IEEE, 86(11), 2278–2324.	Hinton, G.E. & Salakhutdinov, R.R. (2006). Reducing the Dimensionality of Data with Neural Networks. Science, 313(5786), 504–507.	Cortes, C. & Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20, 273–297.
Εναλλακτικές ονομασίες	CNN (Evrişimli Sinir Ağı — Sınıflandırma), CNN classification, ConvNet, convolutional network classifier	Otokodlayıcı (Autoencoder), otokodlayıcı, auto-encoder, encoder-decoder network	Destek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier
Συναφείς	5	4	5
Σύνοψη	A 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.	The Support Vector Machine, introduced by Corinna Cortes and Vladimir Vapnik in 1995, is a classifier that finds the optimal separating hyperplane between classes in a high-dimensional space. It chooses the boundary that leaves the widest possible margin to the nearest training points, which makes its decisions robust on new data.