Neural networks McCulloch-Pitts model

Artificial Neural Networks (ANNs) attempt to emulate their biological counterparts. McCulloch and Pitts (1943) proposed a simple model of a neuron, and Hebb (1949) described a technique which became known as Hebbian learning. Rosenblatt (1961), devised a single layer of neurons, called a Perceptron, that was used for optical pattern recognition. 

Neural networks are essentially non-linear regression models based on a binary threshold unit (McCulloch and Pitts, 1943). The structure of neural networks, called a perception, consists of a set of nodes at different layers where the node of a layer is linked with all the nodes of the next layer (Rosenblatt, 1962). The role of the input layer is to feed input patterns to intermediate layers (also called hidden layers) of units that are followed by an output result layer where the result of computation is read-off. Each one of these units is a neuron that computes a weighted sum of its inputs from other neurons at a previous layer, and outputs a one or a zero according to whether the sum is above or below a... 

Neural networks are algorithmic systems introduced by McCulloch and Pitts in 1943 [24]. Their main advantage, compared with deterministic models, is their ability to provide information about the system to be modeled without prior knowledge of the physical process and identification of the mechanisms involved. Another important advantage of neural networks, compared to the data-based models like regressions or polynomials, is that they are non-linear parsimonious approximators, involving modeling of non-linear industrial processes with a rninimum number of parameters [25]. 

Warren McCulloch and Walter Pitts [4] have proposed a model for a neuron, which still remains the fundamental unit for the majority of neural networks (Figure 12.1). The main elements of a neuron are synapses or weights, an additional element and an activation function. The inputs of the neuron are combined into a weighted sum which is then passed through a nonlinear transformation called the activation function. Each connection has attached a weight that reflects its importance. 

Fortunately, ANNs can overcome these limitations and be used to develop models for these types of data. Some of the earliest work with neural networks was done by McCulloch and Pitts in 1943. ANNs can be used for the evaluation of nonlinear data for the development of a predictive model. Thus, a nonlinear data set, such as the class system of CPT data in the USDA archive, can be used to develop a model and predict compound activities based on the compound structures and associated repellent activities that were incorporated into the neural network. Three-layer neural networks with different architectures were applied to the data sets of acylpiperidines in this chapter. 

---