{
  "id": "cond-mat/0204054",
  "version": "v1",
  "published": "2002-04-02T13:17:58.000Z",
  "updated": "2002-04-02T13:17:58.000Z",
  "title": "Theory of Interacting Neural Networks",
  "authors": [
    "Wolfgang Kinzel"
  ],
  "comment": "Contribution to Networks, ed. by H.G. Schuster and S. Bornholdt, to be published by Wiley VCH",
  "categories": [
    "cond-mat.dis-nn"
  ],
  "abstract": "In this contribution we give an overview over recent work on the theory of interacting neural networks. The model is defined in Section 2. The typical teacher/student scenario is considered in Section 3. A static teacher network is presenting training examples for an adaptive student network. In the case of multilayer networks, the student shows a transition from a symmetric state to specialisation. Neural networks can also generate a time series. Training on time series and predicting it are studied in Section 4. When a network is trained on its own output, it is interacting with itself. Such a scenario has implications on the theory of prediction algorithms, as discussed in Section 5. When a system of networks is trained on its minority decisions, it may be considered as a model for competition in closed markets, see Section 6. In Section 7 we consider two mutually interacting networks. A novel phenomenon is observed: synchronisation by mutual learning. In Section 8 it is shown, how this phenomenon can be applied to cryptography: Generation of a secret key over a public channel.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2002-04-02T13:17:58.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "interacting neural networks",
      "time series",
      "static teacher network",
      "public channel",
      "typical teacher/student scenario"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable",
      "adsabs": "2002cond.mat..4054K"
    }
  }
}