Hybrid knowledge base

Most AI methods used in science lie within one of three areas evolutionary methods, neural networks and related methods, and knowledge-based systems. Additional methods, such as automated reasoning, hybrid systems, fuzzy logic, and case-based reasoning, are also of scientific interest, but this review will focus on the methods that seem to offer the greatest near-term potential in science. 

C Undey, E Tatara, BA Williams, G Birol, and A Cinar. A hybrid supervisory knowledge-based system for monitoring penicillin fermentation. In Proc. American Control Conf., volume 6, pages 3944-3948, Chicago, IL, 2000. 

Rabelo, L. (1990), Hybrid Artificial Neural Networks and Knowledge-Based Expert Systems Approach to Flexible Manufacturing System Scheduling, PhD. dissertation. University of Missouri-Rolla. 

Fig. 8.29. How does the hybridization concept help The figure shows the all important (proteins) example of the peptide bond, (a) We assume a certain pattern of the chemical bonds (this choice is knowledge based) ignoring other possibilities, such as the isomers shown in (b). Apart from the methyl groups (they have the familiar tetrahedral configuration) the molecule is planar. Usually in chemistry, knowing the geometry, we make a conjecture pertaining to the hybridization of particular atoms. This leads to the electron count for each atom the electrons left are supposed to participate in bonds with other atoms. In the example shown, the sjp hybridization is assumed for the central carbon and for the nitrogen and o gen atoms (c). A ir bonding interaction of the nitrogen, carbon and o gen should therefore stabilize the planarity of the system, which is indeed an experimental fact.

---