Semantic nets

Hendler s (1991) hybrid model combines a semantic network with a neural network, as shown in Figure 12.5. In essence, this model depends upon the neural net to learn the internal representations (i.e., the essential microfeatures) that are associated with a set of input stimuli. Thus, the model develops the hidden unit layer of the network as well as the weights connecting the hidden units to the output units. After the network has settled (i.e., has learned to classify the inputs appropriately), the top two layers of units are accessed by the semantic network model by means of spreading activation. Thus, the nodes of the neural net communicate with the nodes of the semantic net. 

Cases can be represented in a variety of formalisms like frames, objects, predicates, semantic nets, and rules. Cases are usually indexed to allow fast and efficient retrieval. Several guidelines on indexing have been proposed by CBR researchers [17,18]. Both manual and automated methods have been used to select indices. Choosing indices manually involves deciding a case s purpose with respect to the aims of the reasoner and deciding under what circumstances the case will be useful. Indices can be automatically constructed on several paradigms ... 

Schubert, L.K., Semantic Nets Are in the Eye of the Beholder, in Principles of Semantic Networks Explorations in the Representation of Knowledge, Sowa, J.F., Ed., Morgan Kaufmann Publishers, San Mateo, CA, 1991, 95. 

There is more about data mining in Chapter 9, but there is an important reason for bringing it up here. When we focus on prediction such as the chance of getting Alzheimer s and congestive heart failure, the mind/concept maps or semantic nets expressed in similar information theoretic terms reduce to the same inference process as described above. This would be clearer to the statistically minded if a simple small table could show all rules, triples, and so on, especially as the technique becomes more complicated. The data could also be probabilities (in which case values are multiplied, not added), which would then bring us very close to an alternative technique called a Bayes s net or Bayesian net, after the bishop who published his ideas in Philosophical Transactions back in 1763. 

Complementary forms of knowledge representation are based on semantic nets and frames (Figure 8.2). Often, they represent just another form to input knowledge. The internal representation is usually based on the predicate calculus. The latter can also be interpreted as a relation of objects ... 

Figure 8 Representation of knowledge in the form of semantic nets (a) and frames (b).

Keywords Product concepts Automotive development system Simultaneous engineering System landscape of engineering IT Semantic nets Service orientated architecture Code of PLM openness ISO 10303-242 ISO 14306 Knowledge based design... 

There are several forms of nets , including neural nets (see Neural Networks in Chemistry) and semantic nets. A semantic net consists of a set of nodes which can represent any type of fact given above, and a set of links between the nodes which represents their interrelations. The links often have names such as IS-A, HAS-PART, BONDED-TO, etc. Chemical examples may have links which correspond to forces, distances, etc. Learning programs often favor nets since they can search for common subgraphs with identical links or nodes, and attempt to generalize the contents of the nodes or links respectively. 

Goranson, H. T., Deep Periodic Structure in Semantic Nets and Related Operating Grammars, in Computers and Mathematics with Applications, to appear, 1990. 

To represent more complex knowledge structures, a number of schemes have been developed e.g.,(i) Semantic nets which can describe both events and objects. Information is represented as sets of nodes connected to each other by arcs. Nodes represent objects and the arcs represent relationships between the nodes. (ii) Frames which consist of a collection of slots that describe aspects of the objects. Procedural information can also be associated with a slot and related frames can be grouped together to form a frame system. 

---