課程綱要

機器學習

課程綱要 實驗項目 上課時數
Introduction to Pattern Recognition and Machine Learning 上課 6 小時

實驗   小時

Probability Distributions

  • Bayesian Probabilities & Bayesian Curve Fitting
  • beta and Dirichlet distributions
  • Gaussian Distribution
Implement Bayesian inference for the Gaussian on MATLAB 上課 3 小時

實驗 9 小時

Decision Theory

  • Minimizing the Expected Loss

Information Theory

Model Selection

上課 6 小時

實驗   小時

Linear Models for Regression

  • Maximum Likelihood, Least Squares & Regularized Least Squares
  • Bayesian Linear Regression & Bayesian Model Comparison

Linear Models for Classification

  • Perceptron Algorithm
  • Probabilistic Discriminant Function – Logistic Regression
  • Laplace Approximation – Model Comparison and BIC
  • Bayesian Logistic Regression
Implement Linear Models for Regression or Classification on MATLAB, and analysis

 

上課 3 小時

實驗 9 小時

Neural Networks

  • feed-forward network & error propagation
  • deep model construction and estimation
Implement Neural Networks on MATLAB, and analysis

 

上課6小時

實驗9小時

實驗內容說明:

實驗項目 內容說明 所需設備
Implement Bayesian inference for the Gaussian on MATLAB 將課程所講解之演算法輔以資料實作及分析,熟悉貝氏理論的推導及其實現 自有設備:有

 

Implement Linear Models for Regression or Classification on MATLAB, and analysis

將課程所講解之演算法輔以資料實作及分析,熟悉Linear Regression的推導及其實現 自有設備:有

 

Implement Neural Networks on MATLAB, and analysis

將課程所講解之演算法輔以資料實作及分析,熟悉Neural Networks的推導及其實現 自有設備:有

 

Implement Deep Learning Machine on MATLAB, and analysis

將課程所講解之演算法輔以資料實作及分析,熟悉Deep Model的推導及其實現

自有設備:有