Timeline for What else beyond convnets is needed to detect sameness in a Bongard problem?
Current License: CC BY-SA 4.0
4 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Apr 1, 2023 at 10:49 | comment | added | Jaume Oliver Lafont | Yes. So in this scheme (ACNN, autoconvolutional neural networks), one single parameter is to be learned, the threshold to separate classes. This would be translation invariant, but not wrt rotation or size change. | |
| Mar 31, 2023 at 21:40 | comment | added | Jaume Oliver Lafont | Without the splitting, I think that convolving the negative image with itself, then normalizing the maximum wrt the energy of the image, yields about 1/2 for sameness and close to 0 for different. | |
| Mar 31, 2023 at 14:19 | comment | added | Jaume Oliver Lafont | Thanks. Do you mean attention as in transformers? | |
| Mar 29, 2023 at 10:14 | history | asked | Jaume Oliver Lafont | CC BY-SA 4.0 |