We will build formulas for the first training row (X1=0, X2=0, Target=0) in columns F through K.

For Row 20 (representing XOR training case 1):

  • Hidden Layer Activation (Sigmoid): Formula: =1/(1+EXP(-Z))
  • Output Layer Input (Z2):
  • Output Prediction:

    • Copy this block of formulas down for rows 21, 22, 23 (the other 3 training cases).

  • dLoss_dWout ($\frac\partial L\partial W_out$): (Gradient for weights from hidden to output)

  • dLoss_dBout ($\frac\partial L\partial b_out$):

    • Enter the XOR truth table:

    | A | B | C | | :--- | :--- | :--- | | X1 | X2 | Y (Target) | | 0 | 0 | 0 | | 0 | 1 | 1 | | 1 | 0 | 1 | | 1 | 1 | 0 |