Machine Learning Tutorials

These are my "notes" as I go through Machine Learning courses and tutorials.

Contents

• Models
  • Linear Regression
    • Loss Function
    • Gradient Descent
    • Mean Squared Error
  • Deep Neural Networks
    • Non-Linear Boundaries
    • Architecture
    • Feedforward
    • Error Function (Cross Entropy Loss)
    • Backpropagation
  • Image Recognition
    • The MNIST Dataset
    • The MNIST Network Model
    • The Training and Test Sets
    • Underfitting
    • Overfitting
    • Notes on Implementing the Model
  • Convolutional Neural Networks
    • Improvements on the Image Recognition Model
    • Architecture
      • Convolutional Layer
      • ReLU
      • Pooling Layer
      • ... and repeat
      • Fully-Connected Layer
  • Transfer Learning
    • What is it?
    • When is it used?
    • How does it work?
  • Style Transfer
    • What is it?
    • How does it work?
• Components
  • Tensors
  • Perceptron
  • Softmax
  • OneHotEncoding

Tools

• PyTorch
• Simulators
  • http://playground.tensorflow.org

References

• Welcome to PyTorch Tutorials
• PyTorch for Deep Learning and Computer Vision
  • Course Page
  • Course Codes
  • Transcript
    • Linear Regression