Feedforward neural networks

An ANN is a network of single neurons jointed together by synaptie eonneetions. Figure 10.22 shows a three-layer feedforward neural network. 

R. Keshavaraj, R. W. Tock, and D. Haycook, Feedforward Neural Network Modeling of Biaxial Deformation of Airbag Fabrics ANTEC 95 Proceedings, SPE Technical Papers, Modeling of Polymer Properties and Processes, Boston (May 1995). 

P. Deveka and L. Achenie, On the use of quasi-Newton based training of a feedforward neural network for time series forecasting. J. Intell. Fuzzy Syst., 3 (1995) 287-294. 

G. Castellano, A.M. Fanelli and M. Pelillo, An iterative pruning algorithm for feedforward neural networks. IEEE Trans. Neural Networks, 8 (1997) 519-531. 

We have already met one tool that can be used to investigate the links that exist among data items. When the features of a pattern, such as the infrared absorption spectrum of a sample, and information about the class to which it belongs, such as the presence in the molecule of a particular functional group, are known, feedforward neural networks can create a computational model that allows the class to be predicted from the spectrum. These networks might be effective tools to predict suitable protective glove material from a knowledge of molecular structure, but they cannot be used if the classes to which samples in the database are unknown because, in that case, a conventional neural network cannot be trained. 

Dayal, B. S., MacGregor, J. F., Taylor, P. A., Kildaw, R., and Marcikio, S., Application of Feedforward Neural Networks and Partial Least Squares Regression for Modelling Kappa Number in a Continuous Kamyr Digester, Pulp Paper Can., 95(1) 26 (1994)... 

A feedforward neural network brings together several of these little processors in a layered structure (Figure 9). The network in Figure 9 is fully connected, which means that every neuron in one layer is connected to every neuron in the next layer. The first layer actually does no processing it merely distributes the inputs to a hidden layer of neurons. These neurons process the input, and then pass the result of their computation on to the output layer. If there is a second hidden layer, the process is repeated until the output layer is reached. 

The layered structure of feedforward neural networks provides a flexible tool that allows us to relate input data to some desired output, but what if there is no output Can a neural network still do something useful Rather curiously, the answer is yes, if we are prepared to employ a different kind of neural network. Numerous classification tasks exist in science, in which... 

A feedforward neural network consisting of 31 hidden and one output neuron was generated 97% inhibitors and 95% non-inhibitors of the training set were predicted correctly 36 inhibitors and 36 non-inhibitors of a test set, which have not been used to generate the model, were predicted with 91.7% accuracy for inhibitors and 88.9% for non-inhibitor. 

M. Holena, M. Baerns, Feedforward neural networks in catalysis, a tool for the approximation of the dependency of yield on catalyst composition, and for knowledge extraction, Catal. Today, 81 (2003), 485-494. 

Holena, M., Baerns, M., Feedforward neural networks in catalysis, a tool for the approximation of the dependency of yield on catalyst composition, and for knowledge extraction, Catal. Today 2003, 81, 485-494. Serra, J. M., Corma, A., Argente, E., Valero, S., Botti, V., Neuronal networks for modeling of kinetic reaction data applicable to catalyst scale up and process control and optimization in the frame of combinatorial catalysis, Appl. Catal. A 2003, 254, 133-145. 

Sanger, T.D. (1989) Optimal unsupervised learning in a single-layer linear feedforward neural network. Neural Networks, 2, 359 173. 

Setiono, R. (1997b). A penalty-function approach for pruning feedforward neural networks. Neural Comput 9,185-204. 

Z Wang, C Di Massimo, MT Tham, and AJ Morris. Procedure for determining the topology of multilayer feedforward neural networks. Neural Networks, 7(2) 291-300, 1994. 

Z Wang, MT Tham, and AJ Morris. Multilayer feedforward neural networks A canonical form approximation of nonlinearity. Int. J. Control, 56(3) 655-672, 1992. 

Application of artificial neural networks (ANN) for modelling of the kinetics of a catalytic hydrogenation reaction in a gas-liquid-solid system has been studied and discussed. The kinetics of the hydrogenation of 2,4-DNT over a palladium on alumina catalyst has been described with feedforward neural networks of dififerent architectures. A simple experimental procedure to supply learning data has been proposed. The accuracy and flexibility of the hybrid first principles-neural network model have been tested and compared with those of the classical model. 

The basic feedforward neural network performs a non-linear transformation of the input data in order to approximate the output data. This net is composed of many simple, locally interacting, computational elements (nodes/neurons), where each node works as a simple processor. The schematic diagram of a single neuron is shown in Fig 1. The input to each i-th neuron consists of a A-dimensional vector X and a single bias (threshold) bj. Each of the input signals Xj is weighted by the appropiate weight Wij, where] = 1- N. 

Figure 3, Schematic diagram of the feedforward neural network...

Scarcelli, F., Tsoi, A.C. Universal Aproximation using Feedforward Neural networks A survey of some existing methods and some new results. Neural Networks 11, 15-37 (1998) Simon, S.A., De Araujo, I.E., Gutierrez, R., Nicolelis, M.A. The neural mechanisms of gustation a distributed processing code. Nature Rev. Neurosci. 7, 890-901 (2006)... 

The performance of a neural network is explored here for classification of two-dimensional input data by means of a feedforward neural network. The simulated data are known from Example 5.12 and describe 200 cases from four classes (Figure 8.16). 

Figure 8.16 Decision boundaries of a feedforward neural network trained by a Bayesian regulation (a) and a conjugate gradient backpropagation algorithm (b).

Feedforward neural networks (FNNs) are the most common type of NN, which have been used in a wide variety of real-world applications, including pattern recognition and classification, system identification and control, and forecasting. Applications of FNNs in fashion supply chain operations involve prediction, classification and model identification (Guo et al, 2011). 

Feedforward neural network (FNN) with one hidden layer. 

Huang, G.B., Zhu, Q.Y. and Siew, C.K., 2004. Extreme learning machine a new learning scheme of feedforward neural networks. Proceedings of the International Joint... 

Russell, S. andNorvig, R, 1994. Artificial Intelligence A Modem Approach, Pve,niicQY a. Scarselli, F. and Tsoi, A., 1998. Universal approximation using feedforward neural networks A survey of some existing methods, and some new results. Neural Networks, 11 (1), 15-37. 

Wong, W.K., Guo, Z.X. and Leung, S.Y.S., 2010. Partially coimected feedforward neural networks on Apollonian networks. Physica A - Statistical Mechanics and its Applications, 389 (22), 5298-5307. 

P. Cleij and R. Hoogerbrugge, Anal. Chim. Acta, 348,495 (1997). Linear Data Prelection Using a Feedforward Neural Network. 

---