Neural Network Basics

A number of researchers have tried training neural networks to achieve color constancy. A neural network basically consists of a set of nodes connected by weights (McClelland and Rumelhart 1986 Rumelhart and McClelland 1986 Zell 1994). Artificial neural networks are an abstraction from biological neural networks. Figure 8.2 shows a motor neuron in (a) and a network of eight artificial neurons on the right. A neuron may be in one of... 

Neural Network Basics Neural Network Control Systems Summary... 

D. Rumelhart, R. Durbin, R. Golden, Y. Chauvin, Backpropagfition The Basic Theory in Mathematical Perspectives on Neural Networks, P. Smolensky, M. C. Mozer, D. E. Rumelhart (Eds.), Lawrence Earlbaum Assoc, Hillsdale, NJ, 1996, pp. 533-566. 

The basic component of the neural network is the neuron, a simple mathematical processing unit that takes one or more inputs and produces an output. For each neuron, every input has an associated weight that defines its relative importance, and the neuron simply computes the weighted sum of all the outputs and calculates an output. This is then modified by means of a transformation function (sometimes called a transfer or activation function) before being forwarded to another neuron. This simple processing unit is known as a perceptron, a feed-forward system in which the transfer of data is in the forward direction, from inputs to outputs, only. 

Bourquin J, Schmidli H, van Hoogevest P, Leuenberger H. Basic concepts of artificial neural networks (ANN) modelling in the application to pharmaceutical development. Pharm Dev Technol 1997 2 95-109. 

A node, the basic component in an artificial neural network. 

In the second stage of the research, a higher level of organization of the biosystems was considered. To this aim, the basic system presented above was used to construct biochemical networks. This was achieved by connecting a number of basic systems according to the principles of neural networks. This part of the research allowed us to delineate the rules for connecting the basic systems into functional biochemical networks and to study the type of information processing that can be achieved in a defined network. 

Neural networks are systems built of basic, mutually interacting elements, called neurons. The two key features of a neural network model that are of interest to us here are the properties of each neuron and the connectivity between neurons. In this section the construction of biochemical networks... 

Enzyme-based biochemical neurons can be built, analyzed, and operated using some of the basic principles of neural networks. 

As a chemometric quantitative modeling technique, ANN stands far apart from all of the regression methods mentioned previously, for several reasons. First of all, the model structure cannot be easily shown using a simple mathematical expression, but rather requires a map of the network architecture. A simplified example of a feed-forward neural network architecture is shown in Figure 8.17. Such a network structure basically consists of three layers, each of which represent a set of data values and possibly data processing instructions. The input layer contains the inputs to the model (11-14). 

The artificial neural network (ANN) is a relatively new technique and possibly the preferred one for current and future (Q)SAR development. Basically, ANNs can be regarded as multinonlinear regression methods. Thus, the neural network software simply multiplies the input by a set of weights that in a nonlinear way transforms the... 

Artificial neural networks (ANNs) are attempts to mimic biological intelligence systems (brains) by copying some of their structure and functions. The basic building block of an ANN is an artificial... 

---