The correct answer is: A. both techniques build models whose output is determined by a linear sum of weighted input attribute values
Neural networks and linear regression are both supervised learning algorithms that can be used to predict a continuous output value from a set of input values. In both cases, the model is built by finding a set of weights that, when applied to the input values, produce the desired output.
In linear regression, the output is determined by a linear sum of the weighted input values. This means that the output is simply the sum of the products of each input value and its corresponding weight.
In neural networks, the output is determined by a more complex function of the input values. This function is typically composed of a series of linear and nonlinear transformations. However, the output is still ultimately determined by a linear sum of the weighted input values.
Option B is incorrect because the output of a neural network can be a continuous or categorical value. Option C is incorrect because the numeric attributes in a neural network do not need to range between 0 and 1. Option D is incorrect because the input attributes in a neural network do not need to be numeric.