Diagnosis of Alzheimer’s Disease Using Dual-Tree Complex Wavelet Transform, PCA, and Feed-Forward Neural Network

Figure 5

Hidden or output layer j. The input j are outputs from the previous layers. These are multiplied by their corresponding weights to configure a weighted sum. A nonlinear activation function is applied to the net input. [The inputs to input j are labeled If unit j was in the first hidden layer, then these inputs would correspond to the input tuple ]