Neural Network With Ms Excel Full | Build

The hard part wasn't making it think; it was making it learn. A neural network learns through "Backpropagation." It looks at the error (Target - Output) and calculates how much each weight contributed to that mistake. It involves calculus—derivatives and the "Chain Rule."

Arthur’s forehead beaded with sweat. He created a row for "Target" in Column D.

Now, he had to build the math to adjust the weights. He needed a section for Gradients.

He calculated the error in cell M2: =D2 - K2. build neural network with ms excel full

Then, the derivative of the Sigmoid function: =K2*(1-K2). And the Delta for the output: =M2 * (K2*(1-K2)).

This was where Excel became a labyrinth. He had to chain these errors backward from the output layer to the hidden layer. He wrote formulas that referenced the output weights, the deltas, and the hidden activations. The formula bars grew long, a chaotic string of cell references like $F$2 and H2.

Finally, he built the Weight Updates. He created a "New Weights" section. The formula was: Old Weight + (Learning Rate * Delta * Input). The hard part wasn't making it think; it was making it learn

He set the Learning Rate (a global variable in cell $Z$1) to 0.1.

The update rule is: New Weight = Old Weight - (Learning Rate * Average Gradient)

Create an "Updated Weights" section next to your initial weights. Now, he had to build the math to adjust the weights

Repeat for all weights and biases.

Sigmoid function: $\frac11+e^-z$

This is the most complex part. We need to compute how much each weight contributed to the error. We will calculate gradients for Output Layer first, then Hidden Layer.