Three-layer perceptron

Figure 3.6 Common representation of a three-layer perceptron.

The three input parameters to the multi-layer perceptron are the atmospheric pressure and the mole fraction of liquid(Xl) and vapor (Yl) phases. The output parameter is the boiling temperature. 

Neural network architectures 2L/FF = two-layer, feed forward network (i.e., perceptron) 3L or 4L/FF = three- or four-layer, feed-forward network (i.e., multi-layer perceptron). 

Fig. 5. Basic anatomy of (a) a three-layer feedforward perceptron and (b) a state recurrent neural network.

At last but not least, the main goal of the present work is feature search in spontaneous speech and in emotional response aiming at pre-clinical evaluation in order to define tests for AD diagnosis. These features will define the control group (CR) and the three AD levels (ES, IS and AS). A secondary goal is the optimization of computational cost with the aim of making these techniques useful for real-time applications in real environments. Thus automatic classification will be modeled with this in mind. We have used a Multi Layer Perceptron (MLP) with neuron number in hidden layer (NNHL) of max(Attribute/Number + Classes/Number) and training step (TS) NNHL 10. 

Multilayer perceptron (MLP) network with three layers. 

The signal propagation in the MLF networks is similar to that of the perceptron-like networks, described in Section 44.4.1. For each object, each unit in the input layer is fed with one variable of the X matrix and each unit in the output layer is intended to provide one variable of the Y table. The values of the input units are passed unchanged to each unit of the hidden layer. The propagation of the signal from there on can be summarized in three steps. 

Aires-de-Sousa and Gasteiger used four regression techniques [multiple linear regression, perceptron (a MLF ANN with no hidden layer), MLF ANN, and v-SVM regression] to obtain a quantitative structure-enantioselectivity relationship (QSER). The QSER models the enantiomeric excess in the addition of diethyl zinc to benzaldehyde in the presence of a racemic catalyst and an enan-tiopure chiral additive. A total of 65 reactions constituted the dataset. Using 11 chiral codes as model input and a three-fold cross-validation procedure, a neural network with two hidden neurons gave the best predictions ANN 2 hidden neurons, R pred = 0.923 ANN 1 hidden neurons, R pred = 0.906 perceptron, R pred = 0.845 MLR, R p .d = 0.776 and v-SVM regression with RBF kernel, R pred = 0.748. 

---