Optimal Pixel-to-Shift Standard Deviation Ratio for Training 2-Layer Perceptron on Shifted 60 × 80 Images with Pixel Distortion in Classifying Shifting-Distorted Objects

Romanuke, Vadim V.

doi:10.1515/acss-2016-0008

Abstract

An optimization problem of classifying shifting-distorted objects is studied. The classifier is 2-layer perceptron, and the object model is monochrome 60 × 80 image. Based on the fact that previously the perceptron has successfully been attempted to classify shifted objects with a pixel-to-shift standard deviation ratio for training, the ratio is optimized. The optimization criterion is minimization of classification error percentage. A classifier trained under the found optimal ratio is optimized additionally. Then it effectively classifies shifting-distorted images, erring only in one case from eight takings at the maximal shift distortion. On average, classification error percentage appears less than 2.5 %. Thus, the optimized 2-layer perceptron outruns much slower neocognitron. And the found optimal ratio shall be nearly the same for other object classification problems, when the number of object features varies about 4800, and the number of classes is between two and three tens.

References

[1] K. Fukushima and S. Miyake, “Neocognitron: A new algorithm for pattern recognition tolerant of deformations and shifts in position,” Pattern Recognition, vol. 15, iss. 6, 1982, pp. 455–469. http://dx.doi.org/10.1016/0031-3203(82)90024-3
Search in Google Scholar
[2] K. Fukushima, “Self-organization of shift-invariant receptive fields,” Neural Networks, vol. 12, iss. 6, 1999, pp. 791–801.10.1016/S0893-6080(99)00039-8
Search in Google Scholar
[3] V. V. Romanuke, “An attempt for 2-layer perceptron high performance in classifying shifted monochrome 60-by-80-images via training with pixel-distorted shifted images on the pattern of 26 alphabet letters,” Radioelectronics, informatics, control, no. 2, 2013, pp. 112–118. http://dx.doi.org/10.15588/1607-3274-2013-2-18
Search in Google Scholar
[4] K. Fukushima, “Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position,” Biological Cybernetics, vol. 36, iss. 4, 1980, pp. 193–202.10.1007/BF00344251
Search in Google Scholar
[5] K. Fukushima, “Training multi-layered neural network neocognitron,” Neural Networks, vol. 40, 2013, pp. 18–31. http://dx.doi.org/10.1016/j.neunet.2013.01.001
Search in Google Scholar
[6] G. Arulampalam and A. Bouzerdoum, “A generalized feedforward neural network architecture for classification and regression,” Neural Networks, vol. 16, iss. 5–6, 2003, pp. 561–568. http://dx.doi.org/10.1016/S0893-6080(03)00116-3
Search in Google Scholar
[7] C. Yu, M. T. Manry, J. Li, and P. L. Narasimha, “An efficient hidden layer training method for the multilayer perceptron,” Neurocomputing, vol. 70, iss. 1–3, 2006, pp. 525–535. http://dx.doi.org/10.1016/j.neucom.2005.11.008
Search in Google Scholar
[8] V. V. Romanuke, “Setting the hidden layer neuron number in feedforward neural network for an image recognition problem under Gaussian noise of distortion,” Computer and Information Science, vol. 6, no. 2, 2013, pp. 38–54. http://dx.doi.org/10.5539/cis.v6n2p38
Search in Google Scholar
[9] V. V. Romanuke, “Dependence of performance of feed-forward neuronet with single hidden layer of neurons against its training smoothness on noised replicas of pattern alphabet,” Bulletin of Khmelnitskiy National University. Technical Sciences, no. 1, 2013, pp. 201–206.
Search in Google Scholar
[10] V. V. Romanuke, “A 2-layer perceptron performance improvement in classifying 26 turned monochrome 60-by-80-images via training with pixel-distorted turned images,” Research bulletin of the National Technical University of Ukraine “KPI”, no. 5, 2014, pp. 55–62.10.15588/1607-3274-2013-2-18
Search in Google Scholar
[11] V. V. Romanuke, “Classification error percentage decrement of two-layer perceptron for classifying scaled objects on the pattern of monochrome 60-by-80-images of 26 alphabet letters by training with pixel-distorted scaled images,” Scientific bulletin of Chernivtsi National University of Yuriy Fedkovych. Series: Computer systems and components, vol. 4, iss. 3, 2013, pp. 53–64.
Search in Google Scholar
[12] P. A. Castillo, J. J. Merelo, M. G. Arenas, and G. Romero, “Comparing evolutionary hybrid systems for design and optimization of multilayer perceptron structure along training parameters,” Information Sciences, vol. 177, iss. 14, 2007, pp. 2884–2905. http://dx.doi.org/10.1016/j.ins.2007.02.021
Search in Google Scholar
[13] S. S. Malalur, M. T. Manry, and P. Jesudhas, “Multiple optimal learning factors for the multi-layer perceptron,” Neurocomputing, vol. 149, p. C, 2015, pp. 1490–1501. http://dx.doi.org/10.1016/j.neucom.2014.08.043
Search in Google Scholar
[14] M. T. Hagan and M. B. Menhaj, “Training feedforward networks with the Marquardt algorithm,” IEEE Transactions on Neural Networks, vol. 5, iss. 6, 1994, pp. 989–993. http://dx.doi.org/10.1109/72.329697
Search in Google Scholar
[15] T. Kathirvalavakumar and S. Jeyaseeli Subavathi, “Neighborhood based modified backpropagation algorithm using adaptive learning parameters for training feedforward neural networks,” Neurocomputing, vol. 72, iss. 16–18, 2009, pp. 3915–3921. http://dx.doi.org/10.1016/j.neucom.2009.04.010
Search in Google Scholar
[16] V. V. Romanuke, “Accuracy improvement in wear state discontinuous tracking model regarding statistical data inaccuracies and shifts with boosting mini-ensemble of two-layer perceptrons,” Problems of tribology, no. 4, 2014, pp. 55–58.
Search in Google Scholar
[17] A. Nied, S. I. Jr. Seleme, G. G. Parma, and B. R. Menezes, “On-line neural training algorithm with sliding mode control and adaptive learning rate,” Neurocomputing, vol. 70, iss. 16–18, 2007, pp. 2687–2691. http://dx.doi.org/10.1016/j.neucom.2006.07.019
Search in Google Scholar
[18] S. J. Yoo, J. B. Park, and Y. H. Choi, “Indirect adaptive control of nonlinear dynamic systems using self recurrent wavelet neural networks via adaptive learning rates,” Information Sciences, vol. 177, iss. 15, 2007, pp. 3074–3098. http://dx.doi.org/10.1016/j.ins.2007.02.009
Search in Google Scholar

Optimal Pixel-to-Shift Standard Deviation Ratio for Training 2-Layer Perceptron on Shifted 60 × 80 Images with Pixel Distortion in Classifying Shifting-Distorted Objects

Abstract

Paradigm

My account