What are the adjustable parameters that scale the influence of input features on the neuron's activation?

What are the adjustable parameters that scale the influence of input features on the neuron's activation?

• A. Bias
• B. Weights
• C. Activation Function
• D. Learning Rate

Answer: (B)

Weights determine how much each input feature contributes to the neuron’s activation. The neuron computes a weighted sum of inputs, plus a bias: net input = sum of (weight times input) plus bias. Each weight scales its corresponding input, so increasing a weight makes that input drive the activation more, while decreasing it reduces that influence. After this weighted sum, the activation function applies a nonlinearity to produce the output. The bias shifts the net input without scaling any particular input, the activation function is just the nonlinear transformation, and the learning rate controls how quickly weights (and biases) are updated during training rather than the current influence of inputs.

Weights determine how much each input feature contributes to the neuron’s activation. The neuron computes a weighted sum of inputs, plus a bias: net input = sum of (weight times input) plus bias. Each weight scales its corresponding input, so increasing a weight makes that input drive the activation more, while decreasing it reduces that influence. After this weighted sum, the activation function applies a nonlinearity to produce the output. The bias shifts the net input without scaling any particular input, the activation function is just the nonlinear transformation, and the learning rate controls how quickly weights (and biases) are updated during training rather than the current influence of inputs.