MLP is an artificial neural network formed by elementary processing units, the so-called neurons. A typical neuron model is shown in Figure 1 (Haykin, 2009).
Scheme of a neuron
The main components of the model are:
Sum function: It carries out a linear combination of the neuron inputs through the use of a set of coefficients, known as synaptic weights. Being w=[w0, w1, ..., wk] the vector of coefficients, and x=[1, x1, ..., xk] the input vector, the sum function is given by the scalar product of both vectors.
Activation function: It is a non-linear function, which gives the network its non-linear nature. The most used activation functions are the sigmoid function (its values ranging between 0 and 1) and the hyperbolic tangent, which ranges between –1 and +1.
Best-Matching Unit: The neuron whose weight vector is closest to the input vector in the training process of a self-organizing map.
Neuron: the elementary processing unit that composes an ANN.
Components Plane: Visualization of the two-dimensional map used to represent the results of the self-organizing maps, which provides qualitative information about how the input variables are related to each other for the data set used to train the map.
Self-Organizing Map: ANN used for visualizing low-dimensional views of high-dimensional data.
Multilayer Perceptron: an important class of ANN that typically consists of the input layer, one or more hidden layers of computation nodes, and an output layer. The input signal propagates through the network in a forward direction, on a layer-by-layer basis.
Artificial Neural Network: a massively parallel distributed processor made up of simple processing units, which has a natural propensity for storing experimental knowledge and making it available for use.
Physical Therapy: a health care profession primarily concerned with the remediation of impairments and disabilities through examination, evaluation, diagnosis and physical intervention carried out by physical therapists.