Revision as of 19:23, 15 March 2019 edit Rpswanson3 (talk \| contribs) 11 edits Undid revision 884081153 by 27.61.224.29 (talk) Tag: Undo ← Previous edit		Revision as of 09:20, 25 June 2019 edit undo 81.218.180.173 (talk) →Protocol: The synchronization of the weights begins when the outputs are different and then the Hebbian learning rule is applied. Next edit →
Line 54: ## Compute the value of the output neuron ## Compare the values of both tree parity machines ### Outputs are ~~different~~same: go to 2.1 ### Outputs are ~~same~~different: one of the suitable learning rules is applied to the weights After the full synchronization is achieved (the weights w<sub>ij</sub> of both tree parity machines are same), A and B can use their weights as keys.<br>

Neural cryptography: Difference between revisions