Breast cancer detection using backpropagation neural network with comparison between different neuron

Pawar, Punam Suresh; Patil, D. R.

doi:10.1109/pdgc.2012.6449811

Cited by 3 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Training an MLP is to adjust the weights and thresholds of their units in order to obtain the desired results. When a pattern is initially introduced to the network it produces an output and, after measuring the error between the given and the desired output, the weights are adjusted to reduce this distance (Pawar and Patil, ). This procedure is known as the delta rule.…”

Section: Annsmentioning

confidence: 99%

“…The signal flows through the network, layer by layer, until an answer is produced by the output layer. In the second step, as Pawar and Patil () explain, the given output is compared with the desired answer to this particular pattern. If it is incorrect, the error is calculated.…”

Section: Annsmentioning

confidence: 99%

“…It is a well‐known database used for evaluating classifiers. This database represents a reasonably complex two‐class problem (Taha and Ghosh, ), and has been very often used in published papers in the fields of medical research and pattern recognition studies (Azmi and Cob, ; Pawar and Patil, ; Singh and Gupta, ). This facilitates comparisons with the new results, similar to what Prechelt () noted in relation to the comparison of algorithms.…”

Section: Comparative Studymentioning

confidence: 99%

“…Their best performance was obtained with backpropagation, with an accuracy of 96.63%, followed by SVM with 96.19% and the decision tree with 92.38%. Pawar and Patil () also used the same proportion of 70–30% to obtain an accuracy of 99.0%, which was their best performance with nine neurons in a hidden layer.…”

Section: Comparative Studymentioning

confidence: 99%

See 3 more Smart Citations

An evaluation of the bihyperbolic function in the optimization of the backpropagation algorithm

Miguez

Xavier

Nelson

2014

Int Trans Operational Res

View full text Add to dashboard Cite

The backpropagation algorithm is one of the most used tools for training artificial neural networks. However, this tool may be very slow in some practical applications. Many techniques have been discussed to speed up the performance of this algorithm and allow its use in an even broader range of applications. Although the backpropagation algorithm has been used for decades, we present here a set of computational results that suggest that by replacing bihyperbolic functions the backpropagation algorithm performs better than the traditional sigmoid functions. To the best of our knowledge, this finding was never previously published in the open literature. The efficiency and discrimination capacity of the proposed methodology are shown through a set of computational experiments, and compared with the traditional problems of the literature.The activation function embedded in the neurons of the network is one of the factors believed to be responsible for slowing this process. This happens because of the iterative nature of the network learning process. A slower calculation process slows down the processes involved. Shafie et al. (2012) showed that another reason for this may be the saturation of the activation function used in the hidden and output layers . When the saturation of a unit occurs, the descending gradient takes very small values, even when the output error is still high. There are many versions of the backpropagation algorithm aiming to optimize its performance such as steepest descendent backpropagation, momentum backpropagation, variable learning rate backpropagation, resilient backpropagation, conjugated gradient backpropagation, quasi-Newton algorithms, and Levenberg-Marquardt algorithm . There have been some advances but, as Wilamowski (2013) states, even the very powerful and fast Levenberg-Marquardt algorithm has the necessity of a matrix inversion, in which size is proportional to the number of patterns. Because of such constraint, the algorithm can be used only for small problems. This optimization is still an open question for the research field. The proposal presented in this paper uses a new activation function, the bihyperbolic function, which shows the necessary characteristics and is faster to compute than other sigmoid functions (Xavier, 2005).This paper is organized as follows. In Section 2, we briefly describe the structure of an ANN and the backpropagation algorithm. In Section 3, we present some tests executed to compare the performance of the new proposed activation function, the bihyperbolic function, in contrast with the most used one, the logistic function. The convergence and generalization aspects, as well as the processing time, were evaluated and obtained results were compared with classifiers presented in the literature. Conclusions are drawn in Section 4, where we explain the characteristics of this work that gave these stimulating results. ANNsANNs work by building connections between the mathematical processing units called neurons. Knowledge is coded in the network by the ...

show abstract

Section: Annsmentioning

confidence: 99%

Section: Annsmentioning

confidence: 99%

Section: Comparative Studymentioning

confidence: 99%

Section: Comparative Studymentioning

confidence: 99%

See 2 more Smart Citations