Natural Language Processing (NLP)
Sigmoid and Tanh
ReLU and Variants
Softmax
Cross-Entropy Loss
Mean Squared Error
Hinge Loss
Gradient Descent Variants
Adam and AdaGrad
Learning Rate Scheduling
Dropout
Batch Normalization
Layer Normalization
Weight Decay
Backpropagation
Mini-batch Training
Early Stopping
Curriculum Learning
Previous
7. Classical Machine Learning for NLP
Go to top
Next
9. Recurrent Neural Networks