A weighted sum is the sum of input values after each has been multiplied by its corresponding weight. In neural networks and linear models, it is commonly passed into an activation function or used directly to compute a prediction.
The sum of all the relevant input values multiplied by their corresponding weights. For example, suppose the relevant inputs consist of the following: ---| input weight | -1.3 | 0.6 | 0.4 | The weighted sum is therefore: A weighted sum is the input argument to an activation function.