{
  "id": "1710.05285",
  "version": "v1",
  "published": "2017-10-15T06:43:29.000Z",
  "updated": "2017-10-15T06:43:29.000Z",
  "title": "CNNComparator: Comparative Analytics of Convolutional Neural Networks",
  "authors": [
    "Haipeng Zeng",
    "Hammad Haleem",
    "Xavier Plantaz",
    "Nan Cao",
    "Huamin Qu"
  ],
  "comment": "5 pages. This paper has been accepted by VADL 2017: Workshop on Visual Analytics for Deep Learning",
  "categories": [
    "cs.LG",
    "cs.CV"
  ],
  "abstract": "Convolutional neural networks (CNNs) are widely used in many image recognition tasks due to their extraordinary performance. However, training a good CNN model can still be a challenging task. In a training process, a CNN model typically learns a large number of parameters over time, which usually results in different performance. Often, it is difficult to explore the relationships between the learned parameters and the model performance due to a large number of parameters and different random initializations. In this paper, we present a visual analytics approach to compare two different snapshots of a trained CNN model taken after different numbers of epochs, so as to provide some insight into the design or the training of a better CNN model. Our system compares snapshots by exploring the differences in operation parameters and the corresponding blob data at different levels. A case study has been conducted to demonstrate the effectiveness of our system.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2017-10-15T06:43:29.000Z"
    }
  ],
  "analyses": {
    "subjects": [
      "H.1.2"
    ],
    "keywords": [
      "convolutional neural networks",
      "comparative analytics",
      "large number",
      "cnncomparator",
      "parameters"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 5,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}