{
  "title": "Pattern Classification of Back-Propagation Algorithm Using Exclusive Connecting Network",
  "abstract": "The objective of this paper is to a design of pattern\r\nclassification model based on the back-propagation (BP) algorithm for\r\ndecision support system. Standard BP model has done full connection\r\nof each node in the layers from input to output layers. Therefore, it\r\ntakes a lot of computing time and iteration computing for good\r\nperformance and less accepted error rate when we are doing some\r\npattern generation or training the network.\r\nHowever, this model is using exclusive connection in between\r\nhidden layer nodes and output nodes. The advantage of this model is\r\nless number of iteration and better performance compare with standard\r\nback-propagation model. We simulated some cases of classification\r\ndata and different setting of network factors (e.g. hidden layer number\r\nand nodes, number of classification and iteration). During our\r\nsimulation, we found that most of simulations cases were satisfied by\r\nBP based using exclusive connection network model compared to\r\nstandard BP. We expect that this algorithm can be available to\r\nidentification of user face, analysis of data, mapping data in between\r\nenvironment data and information.",
  "keywords": [
    "Neural network",
    "Back-propagation",
    "classification."
  ],
  "authors": [
    "Insung Jung",
    "Gi-Nam Wang"
  ],
  "values": 1,
  "issue": 12,
  "issn": null,
  "page_start": 1846,
  "page_end": 5,
  "year": "2007",
  "doi": "https://doi.org/10.5281/zenodo.1071960",
  "journal": "International Journal of Electrical, Electronic and Communication Sciences",
  "categories": [
    "Electrical and Computer Engineering"
  ],
  "files": [
    "http://scholarly.org/pdf/display/pattern-classification-of-back-propagation-algorithm-using-exclusive-connecting-network"
  ]
}