Timeline for How do neural networks learn specific features throughout the layers?
Current License: CC BY-SA 4.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 8, 2022 at 14:09 | comment | added | Chillston | Yes, you can say that - I extended the answer to clarify this a bit more | |
| Jul 8, 2022 at 14:09 | history | edited | Chillston | CC BY-SA 4.0 |
added 1492 characters in body
|
| Jul 8, 2022 at 13:37 | vote | accept | levitatmas | ||
| Jul 8, 2022 at 13:37 | comment | added | levitatmas | So what you are saying is as layers progress the function learned become more and more complex in terms of number of input pixels , which can be regarded as capturing more complex features such as nose right ? The only thing that I did not understand how the coarser features are related to the high level features in the network , is it like the many basic functions (like the edge detections ) are added together and then create a function that fires high values when a "nose" detected ? | |
| Jul 8, 2022 at 12:42 | history | edited | Chillston | CC BY-SA 4.0 |
added 323 characters in body
|
| Jul 8, 2022 at 12:03 | history | answered | Chillston | CC BY-SA 4.0 |