Timeline for Serializing and deserializing stable states of Hopfield networks
Current License: CC BY-SA 3.0
7 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Sep 15, 2017 at 5:24 | comment | added | Hans-Peter Stricker | After having understood how the former works I definitely would also try the latter. But starting with transfer seems more tractable, doesn't it. | |
| Sep 14, 2017 at 23:43 | comment | added | Seanny123 | To distill your question further, are you just trying to transfer knowledge between two content-addressable memories or are you also trying to change the state? | |
| Sep 14, 2017 at 17:13 | comment | added | Hans-Peter Stricker | Hopfield networks consist of McCulloch-Pitts neurons (which are good approximations of integrate-and-fire neurons), they are content-addressable memories, they have stable attractors,... That's why I started with them. | |
| Sep 14, 2017 at 17:01 | comment | added | Hans-Peter Stricker | Of course it would. And I used Hopfield networks only because I know them quite well (having attractors and the like). Concerning the greater context: I'll do my best to provide it in an addendum. | |
| Sep 14, 2017 at 16:51 | comment | added | Seanny123 | Given that Hopfield networks are content-addressable memories would it be acceptable for me to post an answer using a different form of content-addressable memory, such as a NEF/SPA associative memory? Additionally, why are you using a Hopfield network? May I ask what the greater context of this extremely interesting question is? | |
| Sep 14, 2017 at 11:15 | history | edited | Hans-Peter Stricker | CC BY-SA 3.0 |
added 187 characters in body
|
| Sep 14, 2017 at 10:58 | history | asked | Hans-Peter Stricker | CC BY-SA 3.0 |