machine learning in action , part 1

标签：

We should think in below four questions:

• the decription of machine learning
• key tasks in machine learning
• why you need to learn about machine learning
• why python is so great for machine learning

1.The author talked some examples about machine learning in our lives.We can know machine learning is used to analysis dataset especially in classify handwirting,detect diease and so on.From buying birthday card to send mail,then got response,machine learning help us a lot.

　　In our world,there are many simple and repeat works.If we can convert the entity of work to data stored in computer,machine learning will learn dataset and give some output.Think it‘s cool.

2.supervised learning and unsupervised learning

supervised learning:in this system,it has a set of training data and test data.Training dataset has some features value and target value.Machine learning accurates the predict by target value.Then,Through compared the answer test set get with correct answer to get the accuracy.

unspervised learning:there is no label or target value given for the data.the one tast is together the simillar group.  Another task of unsupervised learning may be reducing the data from many features to a small number so that we can properly visualize it in two or three dimensions.

          spervised learning tasks

   Classification                     Regression
   k-Nearest Neighbors                Linear 
   Naive Bayes                        Locally weighted linear
   Support vector machines            Ridge
   Decision trees                     Lasso
          
           Unsupervised learning tasks

   Clustering                          Density estimation
   k-Means                             Expectation maximization
   DBSCAN                              Par zen window

3.the doc of Numpy

machine learning in action , part 1

标签：

原文地址：http://www.cnblogs.com/mRRRR/p/5203946.html