=================================================
The paper aim to convert the ordinal regression problem to classification problem, then use the SVM to solve the reduced problem.
The input pair is as follow
loss is formulated like following
The concept of this method is simple, below is a toy example
It simply convert the ranking problem into classification.
Solve the W, find the linear mapping as follow
The equation above is somewhat like the SVM optimization problem.
The pictture bellow shows the result of the mapping.
Comment:
The idea is smart and easy to understand. But the paper use too many notation and math equation which make it hard to read. It should explain the notion in a more general way.
Heya¡my very first comment on your site. ,I have been reading your blog for a while and thought I would completely pop in and drop a friendly note. . It is great stuff indeed. I also wanted to ask..is there a way to subscribe to your site via email?
回覆刪除Function Point Estimation Training