You can choose this command after selecting one PatternList, one Categories and one FFNet.

Settings

Maximum number of epochs

the maximum number of times that the complete PatternList dataset will be presented to the neural net.

Tolerance of minimizer

when the difference in costs between two successive learning cycles is smaller than this value, the minimization process will be stopped.

Cost function

Minimum-squared-error:

  costs = ∑_allPatterns ∑_allOutputs (o_k - d_k)², where

      o_k : actual output of unit k

      d_k : desired output of unit k

Minimum-cross-entropy:

  costs = - ∑_allPatterns ∑_allOutputs (d_k · ln o_k + (1-d_k) · ln (1-o_k))

Algorithm

The minimization procedure is a variant of conjugate gradient minimization, see for example Press et al. (1992), chapter 10, or Nocedal & Wright (1999), chapter 5.

Links to this page

• Feedforward neural networks 1.1. The learning phase
• Feedforward neural networks 2. Quick start
• Feedforward neural networks 4. Command overview
• FFNet & PatternList & ActivationList: Get average costs...
• FFNet & PatternList & ActivationList: Get total costs...
• FFNet & PatternList & Categories: Get average costs...
• FFNet & PatternList & Categories: Get total costs...