{
  "id": "1511.06072",
  "version": "v1",
  "published": "2015-11-19T07:01:36.000Z",
  "updated": "2015-11-19T07:01:36.000Z",
  "title": "Mediated Experts for Deep Convolutional Networks",
  "authors": [
    "Sebastian Agethen",
    "Winston H. Hsu"
  ],
  "categories": [
    "cs.LG",
    "cs.NE"
  ],
  "abstract": "We present a new supervised architecture termed Mediated Mixture-of-Experts (MMoE) that allows us to improve classification accuracy of Deep Convolutional Networks (DCN). Our architecture achieves this with the help of expert networks: A network is trained on a disjoint subset of a given dataset and then run in parallel to other experts during deployment. A mediator is employed if experts contradict each other. This allows our framework to naturally support incremental learning, as adding new classes requires (re-)training of the new expert only. We also propose two measures to control computational complexity: An early-stopping mechanism halts experts that have low confidence in their prediction. The system allows to trade-off accuracy and complexity without further retraining. We also suggest to share low-level convolutional layers between experts in an effort to avoid computation of a near-duplicate feature set. We evaluate our system on a popular dataset and report improved accuracy compared to a single model of same configuration.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2015-11-19T07:01:36.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "deep convolutional networks",
      "mediated experts",
      "share low-level convolutional layers",
      "early-stopping mechanism halts experts",
      "near-duplicate feature set"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable",
      "adsabs": "2015arXiv151106072A"
    }
  }
}