Uploaded image for project: 'Hama'
  1. Hama
  2. HAMA-791

Fix the problem that MultilayerPerceptron fails to learn a good hypothesis sometimes

    XMLWordPrintableJSON

    Details

    • Type: Bug
    • Status: Resolved
    • Priority: Major
    • Resolution: Fixed
    • Affects Version/s: None
    • Fix Version/s: 0.6.3
    • Component/s: None

      Description

      Fix the problem that MultilayerPerceptron fails to learn a good hypothesis sometimes. If the weights of MLP initialized to very bad values, the model might fail the test.

      Since the new model developed in HAMA-770 will replace the current old model, this problem will be simply fixed by increase the training iteration.

        Attachments

        1. HAMA-791.patch
          7 kB
          Yexi Jiang

          Activity

            People

            • Assignee:
              yxjiang Yexi Jiang
              Reporter:
              yxjiang Yexi Jiang
            • Votes:
              0 Vote for this issue
              Watchers:
              2 Start watching this issue

              Dates

              • Created:
                Updated:
                Resolved: