Neuron, artificial

Modeling the Brain Biological Neurons versus Artificial Neurons... 

The nervous systems and especially the brains of animals and humans work very fast, efficiently, and highly in parallel. They consist of networked neurons which work together and interchange signals with one another. This section describes the functionality of a biological neuron and explains the model of an artificial neuron. 

Artificial Neural Networks (ANNs) are information processing imits which process information in a way that is motivated by the functionality of the biological nervous system. Just as the brain consists of neurons which are connected with one another, an ANN comprises interrelated artificial neurons. The neurons work together to solve a given problem. 

Figure 9-13. Artificial neuron the signals x, are weighted (with weights IV,) and summed to produce a net signal Net. This net signal is then modified by a transfer function and sent as an output to other neurons,...

In Figures 9-13 and 9-16 the artificial neurons have been plotted as circles. In order to visualize the weights as well, we will now plot the neurons as columns, consisting of cuboids, where each cuboid represents a weight. 

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. 

The basic model of a single artificial neuron consists of a weighted summer and an activation (or transfer) function as shown in Figure 10.20. Figure 10.20 shows a neuron in the yth layer, where... 

Fig. 10.1 Schematic representations of (a) a biological neuron, and (b) a McCulloch-Pitts artificial neuron.

The presence of polymer, solvent, and ionic components in conducting polymers reminds one of the composition of the materials chosen by nature to produce muscles, neurons, and skin in living creatures. We will describe here some devices ready for commercial applications, such as artificial muscles, smart windows, or smart membranes other industrial products such as polymeric batteries or smart mirrors and processes and devices under development, such as biocompatible nervous system interfaces, smart membranes, and electron-ion transducers, all of them based on the electrochemical behavior of electrodes that are three dimensional at the molecular level. During the discussion we will emphasize the analogies between these electrochemical systems and analogous biological systems. Our aim is to introduce an electrochemistry for conducting polymers, and by extension, for any electrodic process where the structure of the electrode is taken into account. 

Such clear postsynaptic potentials can be recorded intracellularly with microelectrodes in large quiescent neurons after appropriate activation but may be somewhat artificial. In practice a neuron receives a large number of excitatory and inhibitory inputs and its bombardment by mixed inputs means that its potential is continuously changing and may only move towards the threshold for depolarisation if inhibition fails or is overcome by a sudden increase in excitatory input. 

Aqueous solubility is selected to demonstrate the E-state application in QSPR studies. Huuskonen et al. modeled the aqueous solubihty of 734 diverse organic compounds with multiple linear regression (MLR) and artificial neural network (ANN) approaches [27]. The set of structural descriptors comprised 31 E-state atomic indices, and three indicator variables for pyridine, ahphatic hydrocarbons and aromatic hydrocarbons, respectively. The dataset of734 chemicals was divided into a training set ( =675), a vahdation set (n=38) and a test set (n=21). A comparison of the MLR results (training, r =0.94, s=0.58 vahdation r =0.84, s=0.67 test, r =0.80, s=0.87) and the ANN results (training, r =0.96, s=0.51 vahdation r =0.85, s=0.62 tesL r =0.84, s=0.75) indicates a smah improvement for the neural network model with five hidden neurons. These QSPR models may be used for a fast and rehable computahon of the aqueous solubihty for diverse orgarhc compounds. 

A more recently introduced technique, at least in the field of chemometrics, is the use of neural networks. The methodology will be described in detail in Chapter 44. In this chapter, we will only give a short and very introductory description to be able to contrast the technique with the others described earlier. A typical artificial neuron is shown in Fig. 33.19. The isolated neuron of this figure performs a two-stage process to transform a set of inputs in a response or output. In a pattern recognition context, these inputs would be the values for the variables (in this example, limited to only 2, X and x- and the response would be a class variable, for instance y = 1 for class K and y = 0 for class L. 

Fig. 33.19. An artificial neuron. The inputs are weighted and summed according to S = vviXi + W2X2, S is transformed by comparison with T and leads to a 0/1 value for y.

The structural unit of artificial neural networks is the neuron, an abstraction of the biological neuron a typical biological neuron is shown in Fig. 44.1. Biological neurons consist of a cell body from which many branches (dendrites and axon) grow in various directions. Impulses (external or from other neurons) are received through the dendrites. In the cell body, these signals are sifted and integrated. 

Fig. 44.2. An artificial neuron x,. ..Xp are the incoming signals wi... Wp are the corresponding weight factors and F is the transfer function.

The oscillation of membrane current or membrane potential is well-known to occur in biomembranes of neurons and heart cells, and a great number of experimental and theoretical studies on oscillations in biomembranes as well as artificial membranes [1,2] have been carried out from the viewpoint of their biological importance. The oscillation in the membrane system is also related to the sensing and signal transmission of taste and olfaction. Artificial oscillation systems with high sensitivity and selectivity have been pursued in order to develop new sensors [3-8]. 

In both Navanax neurons (65) and an artificial phospholipid bilayer membrane (66). salicylic acid (1-30 mM) increased K" " permeability but decreased Cl- permeability resulting in a net Increase in membrane conductance. To account for the selective effect of salicylic acid (and other benzoic acids) on the two permeabilities, it was proposed that the anions of the organic acids adsorb to membranes to produce either a negative surface potential (66) or an increase in the anionic field strength of the membrane (47, 48). 

Fig. 6.19. Components and connection of two artificial neurons, according to Danzer et al. [2001]...

Zeilhofer, H. U., Studler, B Arabadzisz, D. et al. (2005). Glycinergic neurons expressing enhanced green fluorescent protein in bacterial artificial chromosome transgenic mice. J. Comp. Neurol. 482, 123-41. 

In the human brain, it is the combined efforts of many neurons acting in concert that creates complex behavior this is mirrored in the structure of an ANN, in which many simple software processing units work cooperatively. It is not just these artificial units that are fundamental to the operation of ANNs so, too, are the connections between them. Consequently, artificial neural networks are often referred to as connectionist models. 

---