Deep Learning with PyTorch

  1. Advanced Deep Learning Architectures
    1. Autoencoders
      1. Autoencoder Fundamentals
        1. Encoder-Decoder Architecture
          1. Dimensionality Reduction
            1. Reconstruction Loss
            2. Encoder Design
              1. Feature Extraction
                1. Bottleneck Layer
                2. Decoder Design
                  1. Feature Reconstruction
                    1. Output Layer Configuration
                    2. Autoencoder Variants
                      1. Denoising Autoencoders
                        1. Noise Injection
                          1. Robustness Training
                          2. Sparse Autoencoders
                            1. Sparsity Constraints
                              1. L1 Regularization
                              2. Contractive Autoencoders
                                1. Jacobian Regularization
                              3. Variational Autoencoders (VAEs)
                                1. Probabilistic Encoding
                                  1. Latent Space Distribution
                                    1. Reparameterization Trick
                                      1. VAE Loss Function
                                        1. Reconstruction Loss
                                          1. KL Divergence
                                          2. Generative Sampling
                                        2. Generative Adversarial Networks (GANs)
                                          1. GAN Framework
                                            1. Two-Player Game Theory
                                              1. Minimax Objective
                                              2. Generator Network
                                                1. Noise to Data Mapping
                                                  1. Generator Architecture
                                                    1. Generator Loss
                                                    2. Discriminator Network
                                                      1. Real vs Fake Classification
                                                        1. Discriminator Architecture
                                                          1. Discriminator Loss
                                                          2. GAN Training Process
                                                            1. Alternating Training
                                                              1. Training Dynamics
                                                                1. Mode Collapse
                                                                  1. Training Instability
                                                                  2. GAN Variants
                                                                    1. Deep Convolutional GANs (DCGANs)
                                                                      1. Convolutional Architecture
                                                                        1. Training Guidelines
                                                                        2. Conditional GANs
                                                                          1. Conditional Generation
                                                                            1. Class-conditional GANs
                                                                            2. Wasserstein GANs
                                                                              1. Wasserstein Distance
                                                                                1. Improved Training Stability
                                                                            3. Attention Mechanisms
                                                                              1. Attention Concept
                                                                                1. Selective Focus
                                                                                  1. Context-dependent Processing
                                                                                  2. Attention Mechanisms
                                                                                    1. Additive Attention
                                                                                      1. Multiplicative Attention
                                                                                        1. Scaled Dot-Product Attention
                                                                                        2. Self-Attention
                                                                                          1. Query, Key, Value Framework
                                                                                            1. Attention Score Computation
                                                                                              1. Attention Weight Calculation
                                                                                              2. Multi-Head Attention
                                                                                                1. Parallel Attention Heads
                                                                                                  1. Concatenation and Projection
                                                                                                    1. Representation Diversity
                                                                                                  2. Transformer Architecture
                                                                                                    1. Transformer Overview
                                                                                                      1. Attention-based Architecture
                                                                                                        1. Parallelizable Computation
                                                                                                        2. Positional Encoding
                                                                                                          1. Sequence Order Information
                                                                                                            1. Sinusoidal Encoding
                                                                                                              1. Learned Positional Embeddings
                                                                                                              2. Encoder Architecture
                                                                                                                1. Multi-Head Self-Attention
                                                                                                                  1. Feed-Forward Networks
                                                                                                                    1. Residual Connections
                                                                                                                      1. Layer Normalization
                                                                                                                      2. Decoder Architecture
                                                                                                                        1. Masked Self-Attention
                                                                                                                          1. Encoder-Decoder Attention
                                                                                                                            1. Autoregressive Generation
                                                                                                                            2. Transformer Applications
                                                                                                                              1. Natural Language Processing
                                                                                                                                1. Computer Vision
                                                                                                                                  1. Speech Processing

                                                                                                                              Previous

                                                                                                                              7. Recurrent Neural Networks (RNNs) for Sequential Data

                                                                                                                              Go to top

                                                                                                                              Next

                                                                                                                              9. Model Deployment and Production