Computer Vision

  1. Deep Learning for Computer Vision
    1. Neural Network Fundamentals
      1. Perceptron Model
        1. Linear Separability
          1. Perceptron Learning Algorithm
          2. Multi-Layer Perceptrons
            1. Hidden Layers
              1. Universal Approximation Theorem
              2. Activation Functions
                1. Sigmoid Function
                  1. Hyperbolic Tangent
                    1. ReLU and Variants
                      1. Leaky ReLU
                        1. ELU
                          1. Swish
                        2. Backpropagation Algorithm
                          1. Chain Rule Application
                            1. Gradient Computation
                              1. Weight Update Rules
                              2. Loss Functions
                                1. Mean Squared Error
                                  1. Cross-Entropy Loss
                                    1. Hinge Loss
                                    2. Optimization Methods
                                      1. Gradient Descent Variants
                                        1. Stochastic Gradient Descent
                                          1. Mini-Batch Gradient Descent
                                            1. Momentum Methods
                                              1. Adaptive Learning Rate Methods
                                                1. AdaGrad
                                                  1. RMSprop
                                                    1. Adam
                                                2. Convolutional Neural Networks
                                                  1. CNN Architecture Components
                                                    1. Convolutional Layers
                                                      1. Convolution Operation
                                                        1. Kernels and Filters
                                                          1. Stride and Padding
                                                            1. Feature Maps
                                                            2. Pooling Layers
                                                              1. Max Pooling
                                                                1. Average Pooling
                                                                  1. Global Pooling
                                                                    1. Adaptive Pooling
                                                                    2. Fully Connected Layers
                                                                      1. Flattening Operation
                                                                        1. Dense Connections
                                                                      2. Regularization Techniques
                                                                        1. Dropout
                                                                          1. Training vs Inference
                                                                            1. Dropout Variants
                                                                            2. Batch Normalization
                                                                              1. Internal Covariate Shift
                                                                                1. Normalization Process
                                                                                  1. Learnable Parameters
                                                                                  2. Layer Normalization
                                                                                    1. Group Normalization
                                                                                    2. CNN Architectures
                                                                                      1. LeNet-5
                                                                                        1. Historical Significance
                                                                                          1. Architecture Details
                                                                                          2. AlexNet
                                                                                            1. Deep Architecture
                                                                                              1. ReLU Activation
                                                                                                1. Dropout Usage
                                                                                                2. VGGNet
                                                                                                  1. Deep and Narrow Design
                                                                                                    1. Small Filter Sizes
                                                                                                    2. GoogLeNet
                                                                                                      1. Inception Modules
                                                                                                        1. Network in Network
                                                                                                          1. Auxiliary Classifiers
                                                                                                          2. ResNet
                                                                                                            1. Residual Connections
                                                                                                              1. Skip Connections
                                                                                                                1. Deep Network Training
                                                                                                                2. DenseNet
                                                                                                                  1. Dense Connections
                                                                                                                    1. Feature Reuse
                                                                                                                    2. MobileNet
                                                                                                                      1. Depthwise Separable Convolutions
                                                                                                                        1. Efficient Architecture
                                                                                                                        2. EfficientNet
                                                                                                                          1. Compound Scaling
                                                                                                                            1. Neural Architecture Search
                                                                                                                        3. Training Deep Networks
                                                                                                                          1. Data Preparation
                                                                                                                            1. Data Augmentation
                                                                                                                              1. Geometric Transformations
                                                                                                                                1. Photometric Transformations
                                                                                                                                  1. Advanced Augmentation
                                                                                                                                  2. Data Normalization
                                                                                                                                    1. Dataset Splitting
                                                                                                                                    2. Training Strategies
                                                                                                                                      1. Transfer Learning
                                                                                                                                        1. Pretrained Models
                                                                                                                                          1. Feature Extraction
                                                                                                                                            1. Fine-Tuning
                                                                                                                                            2. Progressive Training
                                                                                                                                              1. Curriculum Learning
                                                                                                                                              2. Hyperparameter Optimization
                                                                                                                                                1. Learning Rate Scheduling
                                                                                                                                                  1. Batch Size Selection
                                                                                                                                                    1. Architecture Search
                                                                                                                                                    2. Regularization and Generalization
                                                                                                                                                      1. Weight Decay
                                                                                                                                                        1. Early Stopping
                                                                                                                                                          1. Model Ensembling
                                                                                                                                                          2. Training Monitoring
                                                                                                                                                            1. Loss Curves
                                                                                                                                                              1. Validation Metrics
                                                                                                                                                                1. Gradient Analysis

                                                                                                                                                            Previous

                                                                                                                                                            8. Classical Machine Learning for Vision

                                                                                                                                                            Go to top

                                                                                                                                                            Next

                                                                                                                                                            10. Core Vision Tasks with Deep Learning