Machine Learning (Graduated Course)

• Course Number: EE 6550
• Year: 2022-Spring

Homeworks & Final Project

• HW1 (20%): Maximum A Posteriori probability estimator
  • Predict the classes for "Wine" dataset
• HW2 (20%): Maximum Likelihood (ML) & Bayesian Linear Regression
  • Utilize the Gaussian basis function to form feature vector
  • The final MSE loss (validation loss < 0.01 is achieved)
• HW3 (20%): 2-layer & 3-layer NN handcrafted implementation
  • Implement the back propagation algorithm
  • Use only numpy package to train from scratch
• Final Project (40%): Behavior-Classification-of-Exposition-Visitors