A weighted sum multiplies input signals by scalar coefficients and adds the products. In a neural-network node, a bias is added before the result passes through an activation function. section 11.2
A hidden-node calculation
For input 2.0, a node with weight 0.8 and bias −0.5 produces 0.8 × 2.0 − 0.5 = 1.1, its pre-activation value. section 11.3.2




