What term denotes the constant added to the weighted sum?

What term denotes the constant added to the weighted sum?

• A. Weights
• B. Activation Function
• C. Input
• D. Bias

Answer: (D)

The constant added to the weighted sum is the bias. In a neuron or linear model, you compute the weighted sum of inputs and then add this constant before applying the activation function: z = w·x + b. The bias shifts the activation threshold, allowing the model to fit data even when all inputs are zero. It’s not the weights (which scale inputs), not the inputs themselves, and not the activation function (which nonlinearly transforms the sum after the bias is added). This intercept term gives the model flexibility to fit a wider range of patterns.

The constant added to the weighted sum is the bias. In a neuron or linear model, you compute the weighted sum of inputs and then add this constant before applying the activation function: z = w·x + b. The bias shifts the activation threshold, allowing the model to fit data even when all inputs are zero. It’s not the weights (which scale inputs), not the inputs themselves, and not the activation function (which nonlinearly transforms the sum after the bias is added). This intercept term gives the model flexibility to fit a wider range of patterns.