Jämför metoder

	TextCNN - Textklassificering med convolutional neural networks	Dubbelriktad RNN	Random Forest
Ämnesområde	Djupinlärning	Djupinlärning	Maskininlärning
Familj	Machine learning	Machine learning	Machine learning
Ursprungsår	2014	1997	2001
Upphovsperson	Kim, Y.	Schuster, M. & Paliwal, K.K.	Breiman, L.
Typ	Convolutional neural network (deep learning)	Recurrent neural network (sequence model)	Ensemble (bagging of decision trees)
Ursprungskälla	Kim, Y. (2014). Convolutional Neural Networks for Sentence Classification. EMNLP.	Schuster, M. & Paliwal, K.K. (1997). Bidirectional Recurrent Neural Networks. IEEE Transactions on Signal Processing, 45(11), 2673–2681.	Breiman, L. (2001). Random Forests. Machine Learning, 45, 5–32.
Alias	CNN — Metin Sınıflandırma (TextCNN), convolutional neural network for sentence classification, sentence-level CNN, TextCNN	Çift Yönlü RNN / BiLSTM / BiGRU, bidirectional recurrent neural network, BiLSTM, BiGRU	Rastgele Orman (Random Forest), rastgele orman, random decision forest, bagged tree ensemble
Närliggande	5	5	4
Sammanfattning	TextCNN is a convolutional neural network for text classification, introduced by Yoon Kim in 2014, that applies parallel convolution filters of different window sizes over word embeddings to capture local n-gram patterns. It is fast and effective for sentiment analysis and topic classification.	A Bidirectional RNN, introduced by Schuster and Paliwal in 1997, processes a sequence in both forward and backward directions so that every position has access to its full surrounding context. With LSTM or GRU cells (BiLSTM/BiGRU) it is the standard approach for named-entity recognition, sequence labelling, and speech recognition.	Random Forest is an ensemble learning method, introduced by Leo Breiman in 2001, that grows many decision trees on bootstrap samples of the data and combines their votes to produce strong classification and regression. By pooling many slightly different trees, it produces more accurate and more stable predictions than any single tree.