Timeline for answer to Normalize a feature in this table by smci
Current License: CC BY-SA 3.0
Post Revisions
14 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jun 25, 2018 at 6:02 | comment | added | Deepak Chawla | I have a doubt what is the difference between mean normalization and feature scaling and why we are using both techniques simultaneously..?? | |
| May 3, 2018 at 22:52 | comment | added | smci | @AnnaVopureta: yes, "scaling" can mean either dividing by the min-max range or the s.d. The advantage of the former is the result is bounded to [0,1] or [-1,1], whereas dividing by the sd the result is not bounded, which can cause problems (esp. with outliers) in feature generation or some models. | |
| May 3, 2018 at 16:22 | comment | added | PlsWork | As a side note, an often used alternative is to divide by the standard deviation instead of (f_max - f_min). | |
| Jul 9, 2016 at 18:47 | comment | added | Jossie Calderon |
Shouldn't it be -.366?
|
|
| Mar 17, 2016 at 1:04 | history | edited | smci | CC BY-SA 3.0 |
deleted 18 characters in body
|
| Mar 17, 2016 at 0:51 | history | edited | smci | CC BY-SA 3.0 |
edited body
|
| Mar 17, 2016 at 0:50 | comment | added | smci | @FangCao: Doh! how on earth did I reverse that!? | |
| Mar 15, 2016 at 20:10 | comment | added | Fang Cao | thanks for the answer. but i noticed the last line of code should be (x2-mean(x2)) / (max(x2) - min(x2)) | |
| Jun 9, 2015 at 20:06 | history | edited | smci | CC BY-SA 3.0 |
added 4 characters in body
|
| Jun 9, 2015 at 20:04 | vote | accept | emmeowzing | ||
| Jun 9, 2015 at 19:11 | history | edited | smci | CC BY-SA 3.0 |
added 28 characters in body
|
| Jun 9, 2015 at 19:01 | history | edited | smci | CC BY-SA 3.0 |
deleted 2 characters in body
|
| Jun 9, 2015 at 18:51 | history | edited | smci | CC BY-SA 3.0 |
deleted 2 characters in body
|
| Jun 9, 2015 at 18:46 | history | answered | smci | CC BY-SA 3.0 |