Natural Language Processing (NLP)

  1. Deep Learning Foundations
    1. Neural Network Basics
      1. Perceptrons and Multi-layer Networks
        1. Activation Functions
          1. Sigmoid and Tanh
            1. ReLU and Variants
              1. Softmax
              2. Loss Functions
                1. Cross-Entropy Loss
                  1. Mean Squared Error
                    1. Hinge Loss
                    2. Optimization
                      1. Gradient Descent Variants
                        1. Adam and AdaGrad
                          1. Learning Rate Scheduling
                        2. Regularization Techniques
                          1. Dropout
                            1. Batch Normalization
                              1. Layer Normalization
                                1. Weight Decay
                                2. Training Strategies
                                  1. Backpropagation
                                    1. Mini-batch Training
                                      1. Early Stopping
                                        1. Curriculum Learning

                                      Previous

                                      7. Classical Machine Learning for NLP

                                      Go to top

                                      Next

                                      9. Recurrent Neural Networks