The input data is then passed to the hidden layers. For the sake of simplicity, let's say that we have only one hidden layer, h1, and that within this one hidden layer, we have n neurons, as follows:
The net input, z, into the activation function for each of these hidden neurons is then the input data set vector, X, multiplied by a weight set vector, Wn (corresponding to the weight sets assigned to the n neurons in the hidden layer), where each weight set vector, Wn, contains m weights (corresponding to the m features in our input data set vector X), as follows:
In linear algebra, the product of multiplying one vector by another ...
