Wermter, S. and Sun, R. (eds.). Hybrid Neural Systems. Springer, 2000.  Home/Search   Document Details and Download   Summary   Related Articles   Check

....require the least possible retraining effort and the number of the produced neurules is kept as small as possible. 1. Introduction There has been extensive research activity at combining (or integrating) the symbolic and the connectionist approaches for knowledge representation in expert systems [3, 15, 16, 19]. Especially, there are a number of efforts combining symbolic rules and neural networks that map rules into neural networks [4, 9, 18] In addition, connectionist expert systems [6, 7, 17] are a type of integrated systems that represent relationships between concepts, considered as nodes of a ....

Wermter, S., Sun, R. (eds), Hybrid Neural Systems, Springer-Verlag, Heidelberg, 2000.

....require retraining of the whole affected part of the target knowledge, but of as small portion of it as possible. 1 INTRODUCTION There has been extensive research activity at combining (or integrating) the symbolic and the connectionist approaches for knowledge representation in expert systems [7, 8, 10]. Especially, there are a number of efforts combining symbolic rules and neural networks [2, 3, 6, 9] They give pre eminence to connectionism and use a neural network as a knowledge base. The main objective is to reduce knowledge elicitation from experts to a minimum. In such approaches, ....

S. Wermter and R. Sun (eds), Hybrid Neural Systems. SpringerVerlag, Heidelberg, 2000.

....using NNs is that the number of free parameters is usually too large to be determined efficiently. To have the advantages of both symbolic and nonsymbolic approaches, it is important to integrate them together. For this purpose, many methods have already been proposed in the literature (see [1] [2] and references therein) Talking about integration of DTs and NNs alone, for example, we can design a DT first, and ENN ENN ENN ENN ENN Figure 1: A neural network tree (NNTree) then derive an NN from the DT [3] 5] This method is good for fast design of NNs. Inversely, we can design an NN ....

S. Wermter and R. Sun (Eds.), Hybrid Neural Systems, Springer-Verlag, 2000.

.... Much initial work in the field of internet agents has used manual encoding techniques or simple techniques from information retrieval [24] However, it becomes increasingly apparent that automatic adaptation, learning, dealing with incompleteness and robustness are necessary requirements [33] . Recently, there has been a new focus on machine learning techniques and language processing, for instance for newswires and World Wide Web documents [20; 21; 8] Agents [3; 19] can be designed to perform various tasks, whether they be classification [12; 23] information retrieval and ....

S. Wermter and R. Sun. Hybrid Neural Systems. Springer, Heidelberg, 2000.

....Therefore, the combination of the two types of processes can lead to signi cant advantages in capturing a full range of cognitive capacities. These ideas provide the basis for building complex hybrid cognitive architectures. Dreyfus and Dreyfus (1987) Sun (1995) Waltz and Feldman (1986) and Wermter and Sun (2000), among others (see Further Readings) contain detailed accounts of a variety of examples of the synergistic combination of connectionist and symbolic processes. 3 One Model for All: How Do We Integrate Connectionist and Symbolic Processes in One Architecture Hybrid models likely involve a ....

....system, as a demonstration of possibilities of implementing complex symbolic systems in distributed connectionist models. Additional techniques that may be used to implement rule based reasoning in distributed neural networks include RAAM, hologrophic representation, and tensor products (see Wermter and Sun 2000 for details) 9 Extraction of Symbolic Knowledge from Connectionist Models Many hybrid connectionist models involve extracting symbolic knowledge, especially rules, from trained connectionist networks. For example, some researchers proposed a search based algorithm to extract conjunctive rules ....

[Article contains additional citation context not shown here]

Wermter, S. and R. Sun, (eds.) (2000). Hybrid Neural Systems. Lecture Notes in Articial Intelligence (LNCS 1778), Springer-Verlag, Heidelberg.

No context found.

Wermter, S. and Sun, R. (eds.). Hybrid Neural Systems. Springer, 2000.

No context found.

S. Wermter, and R. Sun (Eds.). Hybrid Neural Systems. Heidelberg, Springer, 2000.

No context found.

S. Wermter, R. Sun, Hybrid Neural Systems, Springer-Verlag, Heidelberg, 2000.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC