This is homework repository for Machine Learning Spring 2017 course at Nanjing University, instructed by Prof.Zhihua Zhou.

The answers for non-coding problem sets can be found in 151250104.pdf , codes can be found in main.py, or the .ipynb files under sub-directories.

Content Outline

1. introduction & Basic ML Concepts (No coding)

2. Linear Models, especially Linear Regression & Logistic Regression.

   Coding: Binomial Logistic Regression with Newton's Method

3. Decision Trees & Neural Networks

   Coding: A single-layer feedforward neural network, and a keras-aided multilayer network

4. Support Vector Machines

   Coding: Use SVM with Sklearn & Do visualization

5. Bayes Classifiers

   Coding: Implement a bayes classifer for data with both discrete and continuous features

6. Ensemble Methods

   Coding: Adaboost Algorithm

7. Final Homework (No coding)

   ​