השוואת שיטות

	רשת עצבית קונבולוציונית (סיווג)	מכונת וקטורים תומכים (סיווג)	טרנספורמר (עיבוד שפה טבעית)
תחום	למידה עמוקה	למידת מכונה	למידה עמוקה
משפחה	Machine learning	Machine learning	Machine learning
שנת המקור	1998	1995	2017
הוגה השיטה	LeCun, Y. et al.	Cortes, C. & Vapnik, V.	Vaswani, A. et al.
סוג	Deep neural network (convolutional)	Maximum-margin classifier (kernel method)	Attention-based deep neural network
מקור מכונן	LeCun, Y., Bottou, L., Bengio, Y. & Haffner, P. (1998). Gradient-Based Learning Applied to Document Recognition. Proceedings of the IEEE, 86(11), 2278–2324.	Cortes, C. & Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20, 273–297.	Vaswani, A. et al. (2017). Attention Is All You Need. NeurIPS.
כינויים	CNN (Evrişimli Sinir Ağı — Sınıflandırma), CNN classification, ConvNet, convolutional network classifier	Destek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier	Transformer Modeli (NLP), attention-based language model, self-attention network, transformer NLP
קשורות	5	5	4
תקציר	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.	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.	The Transformer is an attention-based deep learning model, introduced by Vaswani and colleagues in 2017, that performs text classification, named-entity recognition, and language modelling by letting every token in a sequence attend directly to every other token. It replaced earlier recurrent designs with a self-attention mechanism that processes whole sequences in parallel.