1. Applications
   1. Images
      1. Image classification
      2. Image semantic segmentation
      3. Image retrieval
      4. Object detection
   2. Language
      1. Text classification
   3. Software mining
      1. Software flaw detection
2. History
   1. Receptive field in a single neuron, 1959
   2. Neocognitron, about 1980
   3. Gradient-based CNN for hand-written character recognition, 1998
   4. AlexNet in ImageNet competition, 2012
3. Hierarchical structure
   1. Input: raw data
      1. Types
         1. RGB images
         2. Raw audio data
      2. Properties
         1. 3D tensor
            1. H-row
            2. W-height
            3. 3-channels
   2. Feed-forward
      1. Operations to abstract each layer
         1. Convolution
         2. Pooling
         3. Non-linear activation function
         4. Or combinations
      2. Last layers: objective function
   3. Backpropogation
      1. Loss
         1. Loss functions
            1. Mean Square Error
            2. Cross Entropy Error
      2. Loss in precious layers