An Integer Recurrent Artificial Neural Network for Classifying Feature   Vectors

Brouwer, Roelof K.

doi:10.1142/s0218001400000222

Cited by 13 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This type of network may be used to store memories and can therefore be used to store the exemplars or training elements corresponding to classes. They have found many applications in image processing 34 , optimization 35 and pattern recognition 32 . A feature of the Hopfield network that is desirable for pattern recognition is that these networks can recover desired features from distorted patterns.…”

Section: Introductionmentioning

confidence: 99%

A Solution Method for Truncated Normalized Max Product Fuzzy Set of Equations

Brouwer¹

2003

Int. J. Unc. Fuzz. Knowl. Based Syst.

Self Cite

View full text Add to dashboard Cite

An iterative method of solving a set of equations based on the truncated normalized max product is described. The operation may serve as the transformation for the set of fully connected units in a fully recurrent network that might otherwise consist of linear threshold units. Because of truncation and normalization the network acting under this transformation has a finite number of states and components of the state vector are bounded. Component values however are not restricted to binary values as would be the case if the network consisted of linear threshold units but can now take on the values in the set {0,0.1,..0.9,1}. This means that each unit although still having discrete output can provide finer granularity compared to the case where a linear threshold unit is used. Truncation is natural in hardware implementation where only a finite number of places behind the decimal are retained.

show abstract

Section: Introductionmentioning

confidence: 99%

A Solution Method for Truncated Normalized Max Product Fuzzy Set of Equations

Brouwer¹

2003

Int. J. Unc. Fuzz. Knowl. Based Syst.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The recurrent neural network (RNN) possesses the function of nonlinear associative memory. The FWN is very effectively used in pattern recognition [7] [XI.…”

Section: Introductionmentioning

confidence: 99%

Web-based search system of pattern recognition for the pattern of industrial components by an innovate technology

Fan

Hsiao

Sung

2002 IEEE International Conference on Industrial Technology, 2002. IEEE ICIT '02.

View full text Add to dashboard Cite

This work utilizes the pattern recognition (PR) technologies by Client-Server network structure into a web-based recognizing system. The system uses a recurrent neural network (RNN) with associative memory to perform the action of training and recognition. Client-end engineer is able to draw directly the shape of engineering components by the browser, and the recognition system will proceed with search for the component database of company by the structure of Internet. In this paper, these component pattcma arc stored in the database system. Their properties and specifications are also attached to the data field of each component pattern except the pattern of engineering component. These Component pattems with the approach of database system will be able to improve the capacity of recognition system effectively. In our approach, the recognition system adopts parallel computing, and it will raise the recognition rate of system. Our recognition system is a client-server network structure by Intemet. The last phase join:$ the technology of database matching in process of the recognition, and it will solve the problem of spurious state. In this paper, our study will be carried out in the Yang-Fen Automation Electrical Engineering Company. Therefore, the cooperative plan of above context will be analyzed and discussed in this paper.

show abstract