Timeline for How to transfer declarative knowledge into neural networks
Current License: CC BY-SA 4.0
8 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Nov 12, 2021 at 17:33 | history | edited | Hans-Peter Stricker | CC BY-SA 4.0 |
added 1 character in body
|
| Mar 31, 2021 at 10:11 | answer | added | Kirill Fedyanin | timeline score: 1 | |
| Mar 31, 2021 at 10:07 | comment | added | Hans-Peter Stricker | @OliverMason: Does it make a difference to start with some constant weights? | |
| Mar 31, 2021 at 9:30 | comment | added | Oliver Mason | Normally you start with random weights, and the training process adjusts them so that the mapping input to output is achieved; if you pre-define them with non-random values, you could in theory tell the NN to behave in a particular way (if you could choose the correct values). | |
| Mar 31, 2021 at 9:15 | comment | added | Hans-Peter Stricker | @OliverMason: To the rest what you say, I fully agree: The weights are too much of a black box to make anything into this direction feasible. (In human brains it works!) | |
| Mar 31, 2021 at 9:13 | comment | added | Hans-Peter Stricker | @OliverMason. Thanks for the comment. I would not say "predefine the weights" or "bypass the training" but to complement/adjust/modulate/correct them (it) - or the other way around: let the training do the fine-tuning. | |
| Mar 31, 2021 at 8:53 | comment | added | Oliver Mason | I would say you are right, in that NNs only learn by being shown an input and an output, ie through 'experience'. "Being told" would map onto pre-defining the weights (ie bypass the training algorithm), but I guess they're too much of a black box for that to be feasible. | |
| Mar 31, 2021 at 8:30 | history | asked | Hans-Peter Stricker | CC BY-SA 4.0 |