Learning with Perceptrons

• Supervised learning:
  • Training set:
    • Designed by a "teacher"
    • Sets of matched inputs/outputs ("examples")
  • Training procedure
    • For each input/output pair:
      • Apply the network to the input
      • For each output
        • Compute the "error" (target output - perceptron output)
        • Multiply the error by the learning rate and the gradient of the input (calculated using the output value)
      • For each weight
        • Multiply the input value by the delta
        • Add this result to the weight
      • Don't forget the threshold!