scispace - formally typeset

What is knowledge representation in artificial neural network? 

10 answers found

Formal knowledge representation also enables automated reasoning, which facilitates network knowledge discovery by making implicit statements explicit.


This system has good function for knowledge learning without disadvantages of neural network, which the learned knowledge implied in network is difficult to be understood or interpreted by expert system.


In this article, we discover that encoding syntactic knowledge (part-of-speech tag) in neural networks can enhance sentence/phrase representation.


Artificial Neural Networks present a new paradigm for decision support that is adaptive and capable of integrating knowledge acquisition , problem solving , and learning .


Artificial neural networks are able to take inputs from the processes without knowing the process model, allowing representation of complex engineering systems which are difficult to model either with traditional model-based engineering or knowledge-based expert systems.


The existing knowledge reduces the complexity of neural network model.


This illustrates one potential contribution of artificial neural networks to cognitive informatics: the discovery of novel forms of representation in systems that can accomplish intelligent tasks.


The object-oriented model is very similar to the frame-based knowledge representation used in artificial intelligence.


The knowledge representation has always been concerned probably because it is the most important problem in the field of AI. How to represent knowledge impacts on the dealing with of knowledge. In this paper,it takes us a new knowledge representation which combines object-oriented with the semantic network. This knowledge representation has many advantages such as having the structure in the network,representation naturally and so on. Therefore,many complex things can also be represented. This offers a new method for the field of knowledge representation.


A neural network can qualitatively predict what it has learned.