Build Neural Network With Ms Excel New 【Verified – 2027】
Forward propagation = input → hidden layer → output.
These would work like =SUM() or =LINEST().
| Function | Description | Example |
| :--- | :--- | :--- |
| =NEURAL.NETWORK(...) | Creates a network object reference. | =NEURAL.NETWORK(layers, activations) |
| =NEURAL.TRAIN(network, inputs, targets, [epochs], [lr]) | Trains and returns trained network. | =NEURAL.TRAIN(A1, B2:D100, E2:E100, 500, 0.01) |
| =NEURAL.PREDICT(network, new_inputs) | Forward pass prediction. | =NEURAL.PREDICT(F1, G2:G5) |
| =NEURAL.LOSS(network, inputs, targets) | Returns current loss. | =NEURAL.LOSS(F1, B2:D100, E2:E100) |
| =NEURAL.WEIGHTS(network, layer_from, layer_to) | Returns weight matrix as a dynamic array. | =NEURAL.WEIGHTS(F1, 2, 3) |
Priority: Medium-High
Target release: Excel 2027 or as a free “Excel Advanced Analytics” add-in
Key differentiator from Python in Excel: Persistence, formula-based transparency, no cloud dependency. build neural network with ms excel new
Here is where it gets interesting. Modern Excel allows iterative calculation (File > Options > Formulas > Enable iterative calculation).
We set up circular references for the weights. Each weight cell points to itself minus a learning rate times the gradient.
Formula for Weight W1 (in cell D5):
=D5 - $Learning_Rate * (Gradient_Output * Hidden_1) Forward propagation = input → hidden layer → output
You are watching online gradient descent happen in real-time. Press F9, and the Loss cell goes down. It is hypnotic.
Before you close the tab, understand this: Excel is the most widely used programming environment on earth. It is a massively parallel grid of 17 billion cells. When you strip away the abstraction of torch.nn.Linear, building a network in Excel forces you to confront the raw mechanics of matrix multiplication and the chain rule.
If you can implement backprop in Excel, you don't understand neural networks—you feel them. Here is where it gets interesting
This is the chain rule: δ1 = (δ2 · W2^T) * ReLU_Prime(Z1)
ReLU Prime = 1 if Z1 > 0 else 0.
First, Delta from above (cell N6):
=MMULT(M6#, TRANSPOSE(W2))
Then, apply ReLU mask (cell O6):
=N6# * IF(F6#>0, 1, 0)