Deep Learning Categories

Posted on Edited on In

Multilayer Neural Network

  • Inherit tf.keras.Model can built own neural network
    • Every neural have several weights and a bias, and can handle a full input
  • Use tf.keras.Sequential()

Convolutional Neural Networks (CNN)

  • Can consider the relationship among several pixels
  • Special Layers:
    • Convolutional Layer
      • Won’t change the scale of the input if the stride is 1 * 1
    • Pooling Layer
      • Will generates more features but won’t increase the calculation

Recurrent Neural Networks (RNN)

  • Works well in the time-based classification

  • Make sense of what they’ve seen before, both short and long-term memory

  • Scenarios:

    • Video Processing
    • Speech Processing
    • Sentiment Analysis
    • Time series Data

  • Key Implements

    • What long term memory should be kept or removed
    • What new memory should be remembered as the long term memory
    • What new memory should be remembered as the short term memory

  • Basis

    • Loss function
    • Forward pass
    • Backward propagation
    • Architecture
      • Batch normalization
      • Activation function
      • Drop out

  • CNN

    • Conv layer
    • Pool layer
    • Multi-head

  • VGG, ResNet

  • RNN

  • LSTM

  • CBOW

  • GNN

  • GCN

  • GAN

  • Transformer