Timeline for How do I change my neural network from a classification task to a regression task?
Current License: CC BY-SA 4.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Oct 23, 2023 at 17:16 | answer | added | Dave | timeline score: 2 | |
| Sep 14, 2023 at 11:07 | comment | added | Dave | The obvious move would seem to be to ditch the sigmoid activation function and use the full (non-bucketed) target data. This is theoretically reasonable and should be easy to implement in code. Is there something too limiting about this? | |
| Feb 29, 2020 at 6:33 | comment | added | ackbar03 | There (theoretically) should exist a way to match the crack images to its stress point because of the physical nature of the material and how the crack images are obtained so it should on paper be feasible, just not sure how to go about it. | |
| Feb 29, 2020 at 6:31 | comment | added | ackbar03 | thanks for the comment! To be exact its not exactly "easy" since the current accuracy isn't superb which is why I'm trying to change it into a regression problem. The problem also isn't that well defined but its somewhat related to fault tolerance. Basically there's defects in a material which affects its structural quality and leads to surface cracks. The proper way to measure the quality is to apply stress on it and measure its fracture stress point. The stress point is then classified into quality buckets. I'm trying to see if matching the surface features to its fracture point is possible | |
| Feb 29, 2020 at 5:57 | comment | added | Dave | The activation function in the output node has basically the same purpose as a link function in a GLM. I am curious, however, what kind of classification you’re making that is so easy to turn into a problem with a continuous response variable. | |
| Feb 29, 2020 at 5:51 | history | asked | ackbar03 | CC BY-SA 4.0 |