Neural networks learning process

Stopping criteria. A rule used to terminate the iterative training process for neural network learning or function minimization. To prevent overtraining, the stopping criteria may not be based solely upon the error function for example performance on a validation set is often used to stop training. 

Neural networks are processing systems that work by feeding in some variables and get an output as response to these inputs. The accuracy of the desired output depends on how well the network learned the input-output relationship during training. 

The neural network is capable of modeling non-linear systems. On the basis of supplied training data the neural network learns (trains) the relationship between the process input and output The data have to be examined carefully before they can be used as a training set for a neural network. The training sets consist of one or more input data and one or more output data. After the training of the network, a test-set of data should be used to verify whether the desired relationship was learned. 

Artificial Neural Networks. An Artificial Neural Network (ANN) consists of a network of nodes (processing elements) connected via adjustable weights [Zurada, 1992]. The weights can be adjusted so that a network learns a mapping represented by a set of example input/output pairs. An ANN can in theory reproduce any continuous function 95 —>31 °, where n and m are numbers of input and output nodes. In NDT neural networks are usually used as classifiers... 

Concomitantly with the increase in hardware capabilities, better software techniques will have to be developed. It will pay us to continue to learn how nature tackles problems. Artificial neural networks are a far cry away from the capabilities of the human brain. There is a lot of room left from the information processing of the human brain in order to develop more powerful artificial neural networks. Nature has developed over millions of years efficient optimization methods for adapting to changes in the environment. The development of evolutionary and genetic algorithms will continue. 

Learning in the context of a neural network is the process of adjusting the weights and biases in such a manner that for given inputs, the correct responses, or outputs are achieved. Learning algorithms include ... 

The structure of a neural network forms the basis for information storage and governs the learning process. The type of neural network used in this work is known as a feed-forward network the information flows only in the forward direction, i.e., from input to output in the testing mode. A general structure of a feed-forward network is shown in Fig. I. Connections are made be-... 

C. Hoskins and D.M. Himmelblau, Process Control via artificial Neural networks and reinforced learning. Computers Chem. Eng., 16 (1992) 241-251. 

The brain s remarkable ability to learn through a process of pattern recognition suggests that, if we wish to develop a software tool to detect patterns in scientific or, indeed, any other kind of data, the structure of the brain could be a productive starting point. This view led to the development of artificial neural networks (ANNs). The several methods that are gathered under the ANN umbrella constitute some of the most widely used applications of Artificial Intelligence in science. Typical areas in which ANNs are of value include ... 

Indeed, if the problem is simple enough that the connection weights can be found by a few moments work with pencil and paper, there are other computational tools that would be more appropriate than neural networks. It is in more complex problems, in which the relationships that exist between data points are unknown so that it is not possible to determine the connection weights by hand, that an ANN comes into its own. The ANN must then discover the connection weights for itself through a process of supervised learning. 

The ability of an ANN to learn is its greatest asset. When, as is usually the case, we cannot determine the connection weights by hand, the neural network can do the job itself. In an iterative process, the network is shown a sample pattern, such as the X, Y coordinates of a point, and uses the pattern to calculate its output it then compares its own output with the correct output for the sample pattern, and, unless its output is perfect, makes small adjustments to the connection weights to improve its performance. The training process is shown in Figure 2.13. 

Giles, A. E. Aldrich, C. van Deventer, J. S. J. Hydrometallurgy 1996, 43, 241. Slater, M. J. Aldrich, C. Application of Neural Network and Other Learning Technologies in Process Engineering Mujtaba, I. M. Hussain, M. A. Eds. Imperial College Press London, 2001 3. 

A neural-network-based simulator can overcome the above complications because the network does not rely on exact deterministic models (i.e., based on the physics and chemistry of the system) to describe a process. Rather, artificia] neural networks assimilate operating data from an industrial process and learn about the complex relationships existing within the process, even when the input-output information is noisy and imprecise. This ability makes the neural-network concept well suited for modeling complex refinery operations. For a detailed review and introductory material on artificial neural networks, we refer readers to Himmelblau (2008), Kay and Titterington (2000), Baughman and Liu (1995), and Bulsari (1995). We will consider in this section the modeling of the FCC process to illustrate the modeling of refinery operations via artificial neural networks. 

---