Perceptron networks

Perceptron networks are feedforward, heteroassociative (or may be auto-associative) networks that accept continuous inputs. Within the last five years there have been no chemical applications of perceptrons applications before that time are now largely outmoded by the advent of more powerful ANNs. We mention them briefly for three reasons they have historical significance, they are ubiquitous in neural network texts, and you will find papers that claim to use perceptrons but in actuality do not. 

---

The linear learning machine and the perceptron network 44.4.1 Principle... 

The region from A to D is called the dynamic range. The regions 2 and 4 constitute the most imfwrtant difference with the hard delimiter transfer function in perceptron networks. These regions rather than the near-linear region 3 are most important since they assure the non-linear response properties of the network. It may... 

Gardner, J.W., Craven, M., Dow, C., Hines, E.L (1998) The prediction of bacteria type and culture growth phase by an electronic nose with a multi-layer perceptron network. Meas. Sci. Technol. 9 120-127. 

Three commonly used ANN methods for classification are the perceptron network, the probabilistic neural network, and the learning vector quantization (LVQ) networks. Details on these methods can be found in several references.57,58 Only an overview of them will be presented here. In all cases, one can use all available X-variables, a selected subset of X-variables, or a set of compressed variables (e.g. PCs from PCA) as inputs to the network. Like quantitative neural networks, the network parameters are estimated by applying a learning rule to a series of samples of known class, the details of which will not be discussed here. 

The perceptron network is the simplest of these three methods, in that its execution typically involves the simple multiplication of class-specific weight vectors to the analytical profile, followed by a hard limit function that assigns either 1 or 0 to the output (to indicate membership, or no membership, to a specific class). Such networks are best suited for applications where the classes are linearly separable in the classification space. 

The perceptron network for this problem is shown in Figure 5.1 below. Input from xo, the bias unit, is always -1. The length of the input vector is 2, and there are 18 input vectors in the training set. 

Figure 5.1 Simple perceptron network for training example.

Artificial neural networks (ANNs) are a non-linear function mapping technique that was initially developed to imitate the brain from both a structural and computational perspective. Its parallel architecture is primarily responsible for its computational power. The multilayer perceptron network architecture is probably the most popular and is used here. 

This rule is used in the output layer of the perceptron network Cj is usually 0.0, and C2 is usually a small number such as 0.05. Note that as such, Cj and C2 do not play the roles of learning rate and threshold, respectively. 

The history of perceptrons was briefly outlined in the Introduction. They were one of the first ANN paradigms, and although they have significant shortcomings (they really can solve only linear problems), they contributed to the framework of many current ANNs. Many ANN texts begin with a discussion of perceptrons and then proceed to build on that foundation. To that end, a simple perceptron network is shown in Figure 8. Some authors claim to use per-... 

FigDre 8 A simple perceptron network see Figure 5 for an explanation of the labels. The middle layer is either fully or randomly connected to the input layer. 

Perceptron Network with hard threshold neurons. 

The overall architecture of our proposed system begins with data acquisition of ECG signals, and then the identification of the QRS complex used for the feature extraction procedures. From the QRS waves, coefficients of the polynomial based approach are used as the unique extracted features. By using these coefficients, classification of the features are performed using Multilayer Perceptron Network and finally with this classification results, the identity of unknown attributes can be determined. The proposed model is summarised as in Fig. 1. 

Hybrid Multilayered Perceptron Network Trained by Modified Recursive Prediction Error-Extreme Learning Machine for Tuberculosis Bacilli Detection... 

M.Y. Mashor, Hybrid Multilayered Perceptron Networks , International Journal of Systems Science, 31, (6), pp. 771-785. 2000. 

---