Computer Learning

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. 

While ANNs cannot do anything that would be impossible to accomplish using an alternative algorithmic method, they can execute tasks that would otherwise be very difficult, such as forming a model from sensory data or from data that is extracted from a continuous industrial process for which no comprehensive theoretical model exists. Their principal limitation is that the numerical model that they create, while open to inspection, is difficult to interpret. This is in marked contrast to the model used by expert systems, in which the knowledge of the system is expressed in readily interpreted statements of fact and logical expressions. Nevertheless, the power of the ANN is 

---

Bradshaw D. The computer learns from experts. Financial Times London 27 April 1989. 

Rees C. Neural Computing—Learning Solutions—User Survey. Department of Trade and Industry, London, UK, 1996. 

Kearns, M., and Vazirani, U., An Introduction to Computational Learning Theory. MIT Press, Cambridge, MA. 1994. 

Numerous applications of GAs within science and other fields have appeared in the literature references to a few of them are given at the end of this chapter. The method has been used for computer learning, modeling of epidemics, the scheduling of the production of fine chemicals, the prediction of the properties of polymers, spectral analysis, and a wide variety of other investigations. In this section we consider a few examples of recent applications in chemistry. 

Singh, M., Berger, B., Kim, P. S., Berger, J. M., and Cochran, A. G. (1998). Computational learning reveals coiled-coil like motifs in histidine kinase linker domains. Proc. Natl. Acad. Sci. 95, 2738-2743. 

Turner, J. Manufacturing intelligence. 1991, 8, 12-14. Bentley, P. Product formulation expert system. In Intelligent Software for Product Formulation Rowe, R.C., Roberts, R.J., Eds. Taylor and Erancis London, 1998 27-41. Bradshaw, D. The computer learns from the experts. Einancial Times London April 27th 1989, 26. 

Rees, C. 1996. Neural computing—Learning solutions (user survey). London UK Department of Trade and Industry. 

Linn, M.C. 1995. Designing computer learning environments for Engineering and Computer Science The Scaffolded Knowledge Integration Framework, J. of Science Education and Technology, 4 2, 103 126. 

Vapnik, V., Structure of statistical learning theay . Computational Learning and Probabilistic Reasoning 1996, pp. 3... 

Aside fi om working on your experimental tasks, answer the questions for your specific area in the general question catalogue with the help of the computer learning environment, your textbook, or the Internet. 

Baum, E.B., Boneh, D., and Garrett, C. (1995) On Genetic Algorithms, in Proceedings of the 8th Annual Conference on Computational Learning Theory, ACM Press, New York. 

Training must consist of a combination of formal instruction (e.g., lectcme, discussion, interactive computer learning, video tape, written material), practical training (demonstrations performed by the trainer and practical exercises performed by the trainee), and evaluation of the operator s performance in the workplace. 

---