Two neural networks which are trained on their mutual output bits are analysed using methods of statistical physics. The exact solution of the dynamics of the two weight vectors shows a novel phenomenon: The networks synchronize to a state with identical time dependent weights. Extending the models to multilayer networks with discrete weights, it is shown how synchronization by mutual learning can be applied to secret key exchange over a public channel.
|Original language||American English|
|Title of host publication||Advances in Solid State Physics|
|Editors||Prof. Bernhard Kramer|
|Publisher||Springer Berlin Heidelberg|
|State||Published - 2002|
|Name||Advances in Solid State Physics|