看板 [ CS_SLT2005 ]
討論串[問題] Homework 1
共 4 篇文章
內容預覽： 開啟 | 關閉 | 只限未讀
首頁
上一頁
1
下一頁
尾頁
#4
Re: [問題] Homework 1
推噓0(0推 0噓 0→)留言0則，0人參與, 最新作者rafan (@_@"""")時間20年前 (2005/09/25 15:22), 編輯資訊
0
0
0
內容預覽:
I think you should use cross validation tecnique. taught in class to decide k. After have a k, you. use the whole training data to predict the testing
#3
Re: [問題] Homework 1
推噓0(0推 0噓 0→)留言0則，0人參與, 最新作者hometoofar (家太遠了)時間20年前 (2005/09/25 13:59), 編輯資訊
0
0
0
內容預覽:
Since we are using kNN here, does that mean we don't need to train it? We justuse the training data and kNN to predict what class label should a test
(還有32個字)
#2
Re: [問題] Homework 1
推噓0(0推 0噓 0→)留言0則，0人參與, 最新作者rafan (@_@"""")時間20年前 (2005/09/25 13:03), 編輯資訊
0
0
0
內容預覽:
Homework 1 is using k-nearest neighbor method, not SVM.. Just forget it.The dataset is a multilabel one, i.e.,. one instance can have more than one ta
(還有44個字)
#1
[問題] Homework 1
推噓0(0推 0噓 0→)留言0則，0人參與, 最新作者hometoofar (家太遠了)時間20年前 (2005/09/25 11:30), 編輯資訊
0
0
0
內容預覽:
I have read "A Practical Guide to Support Vector Classification", but I amstill confused about how to do homework 1.. In the guide, the proposed proce
(還有1070個字)
首頁
上一頁
1
下一頁
尾頁