Timeline for Dimension-Hopping in Machine Learning
Current License: CC BY-SA 3.0
8 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| May 30, 2016 at 10:30 | vote | accept | Saurabh Jain | ||
| May 29, 2016 at 18:01 | comment | added | Neil Slater | The age example is supposed to highlight a dataset that does not have dimension-hopping. Age and weight do not "hop" or swap values randomly between examples - they are not interchangeable and the example is showing how odd that would be (and how difficult it would make simple tasks such as linear regression). Pixel values in images (and similar data in many signal processing tasks) do interchange or move easily due to the nature of the problem. | |
| May 27, 2016 at 7:41 | comment | added | Saurabh Jain | @Emre, what I am getting from your answer is that, no matter from which direction a specific property is input, the feature which this specific property causes should be invariant to input dimension of this property. Thanks! :). Still waiting for some more specific answers, otherwise will mark your reply as answer. | |
| May 27, 2016 at 7:29 | comment | added | Martin Thoma | @sdream I only made a comment; Emre gave the answer. (But you should probably still accept it). The point with CNNs is that not only one feature changes when an object is somewhere else, but a complete pattern is at a different input. | |
| May 26, 2016 at 22:19 | comment | added | Emre | I took that to mean age and weight are dependent, but I'm not sure; it's not my presentation! Or maybe they meant they literally use the wrong column and we want to detect that. | |
| May 26, 2016 at 22:10 | comment | added | Martin Thoma | I understand that in Computer Vision one wants to be invariant for places in the image, but I don't get the age example. | |
| May 26, 2016 at 17:44 | history | edited | Emre | CC BY-SA 3.0 |
added 18 characters in body
|
| May 26, 2016 at 17:32 | history | answered | Emre | CC BY-SA 3.0 |