Biomedical subjects

R K Brouwer

Publications and source records attributed to R K Brouwer.

5 recordsLinked to original sources

PubMed2001

A proposed max-product threshold unit for classification of pattern vectors.

This paper proposes a max-product threshold unit (maptu) that can successfully perform dichotomous classifications of pattern vectors. Maptu, with weight vector, w, classifies a pattern vector, x, by comparing x max-prod w to 0.5. Results obtained by other methods in classification of benchmark data are used for comparison to the method using maptu. The benchmark data consists of the Australian credit data set, cervical cell data set, diabetes data set and the iris data set.

Databases, Factual↗

PubMed1999

The backpropagation algorithm in J, a fast prototyping tool for researching neural networks.

This paper illustrates the use of a powerful language, called J, that is ideal for simulating neural networks. The use of J is demonstrated by its application to a gradient descent method for training a multilayer perceptron. It is also shown how the back-propagation algorithm can be easily generalized to multilayer networks without any increase in complexity and that the algorithm can be completely expressed in an array notation which is directly executable through J. J is a general purpose language, which means that its user is given a flexibility not available in neural network simulators or in software packages such as MATLAB. Yet, because of its numerous operators, J allows a very succinct code to be used, leading to a tremendous decrease in development time.

Algorithms↗

PubMed1999

Growing of a Fuzzy Recurrent Artificial Neural Network (FRANN) for pattern classification.

This paper describes a method for growing a recurrent neural network of fuzzy threshold units for the classification of feature vectors. Fuzzy networks seem natural for performing classification, since classification is concerned with set membership and objects generally belonging to sets of various degrees. A fuzzy unit in the architecture proposed here determines the degree to which the input vector lies in the fuzzy set associated with the fuzzy unit. This is in contrast to perceptrons that determine the correlation between input vector and a weighting vector. The resulting membership value, in the case of the fuzzy unit, is compared with a threshold, which is interpreted as a membership value. Training of a fuzzy unit is based on an algorithm for linear inequalities similar to Ho-Kashyap recording. These fuzzy threshold units are fully connected in a recurrent network. The network grows as it is trained. The advantages of the network and its training method are: (1) Allowing the network to grow to the required size which is generally much smaller than the size of the network which would be obtained otherwise, implying better generalization, smaller storage requirements and fewer calculations during classification; (2) The training time is extremely short; (3) Recurrent networks such as this one are generally readily implemented in hardware; (4) Classification accuracy obtained on several standard data sets is better than that obtained by the majority of other standard methods; and (5) The use of fuzzy logic is very intuitive since class membership is generally fuzzy.

Algorithms↗

PubMed1996

Using a feed-forward network to incorporate the relation between attractees and attractors in a generalized discrete Hopfield network.

This paper demonstrates how a feedforward network with constant connection matrices may be used to train a Hopfield style network for pattern recognition. The connection matrix of the Hopfield style network is asymmetric and its diagonal is non-zero. The Hopfield style network referred to as a GDHN is trained to incorporate a relation between attractees and attractors. The attractees represent class samples and the attractors represent class prototypes. The feedforward network is trained using a gradient descent method. Gradients are fed forward in the network to obtain a gradient for a cost function.

Algorithms↗

PubMed1995

Classifying cervical cells using a recurrent neural network by building basins of attraction.

This paper describes the result of classifying cervical cells employing a novel way of using a Hopfield-style neural network for classification. This method could be used as part of an automated cervical screening system. Rather than storing the exemplars (training elements) as stable points, a connection matrix is determined, using perceptron-type learning, such that the exemplars are placed in basins of attraction. The exemplars from different classes of cells are placed in different basins of attraction, with usually more than one basin per training class. A presented element is then classified by the basin of attraction it falls into. Input to the classification consists of one case of feature vectors derived from the cervical cell images; in another case, input consists of the images themselves. Good results were obtained using this technique.

Cervix Uteri↗