Have a personal or library account? Click to login
An Efficient Technique for Size Reduction of Convolutional Neural Networks after Transfer Learning for Scene Recognition Tasks Cover

An Efficient Technique for Size Reduction of Convolutional Neural Networks after Transfer Learning for Scene Recognition Tasks

Open Access
|Dec 2018

References

  1. [1] S. M. Salaken, A. Khosravi, T. Nguyen, and S. Nahavandi, “Extreme learning machine based transfer learning algorithms: A survey,” <em>Neurocomputing</em>, vol. 267, pp. 516–524, 2017. <ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="<a href="https://doi.org/10.1016/j.neucom.2017.06.037" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">https://doi.org/10.1016/j.neucom.2017.06.037</a>">https://doi.org/10.1016/j.neucom.2017.06.037</ext-link><dgdoi:pub-id xmlns:dgdoi="http://degruyter.com/resources/doi-from-crossref" pub-id-type="doi"><a href="https://doi.org/10.1016/j.neucom.2017.06.037" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">10.1016/j.neucom.2017.06.037</a></dgdoi:pub-id>
  2. [2] D. Han, Q. Liu, and W. Fan, “A new image classification method using CNN transfer learning and web data augmentation,” <em>Expert Systems with Applications</em>, vol. 95, pp. 43–56, 2018. <ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="<a href="https://doi.org/10.1016/j.eswa.2017.11.028" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">https://doi.org/10.1016/j.eswa.2017.11.028</a>">https://doi.org/10.1016/j.eswa.2017.11.028</ext-link><dgdoi:pub-id xmlns:dgdoi="http://degruyter.com/resources/doi-from-crossref" pub-id-type="doi"><a href="https://doi.org/10.1016/j.eswa.2017.11.028" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">10.1016/j.eswa.2017.11.028</a></dgdoi:pub-id>
  3. [3] L. Wang, L. Ge, R. Li, and Y. Fang, “Three-stream CNNs for action recognition,” <em>Pattern Recognition Letters</em>, vol. 92, pp. 33–40, 2017. <ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="<a href="https://doi.org/10.1016/j.patrec.2017.04.004" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">https://doi.org/10.1016/j.patrec.2017.04.004</a>">https://doi.org/10.1016/j.patrec.2017.04.004</ext-link><dgdoi:pub-id xmlns:dgdoi="http://degruyter.com/resources/doi-from-crossref" pub-id-type="doi"><a href="https://doi.org/10.1016/j.patrec.2017.04.004" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">10.1016/j.patrec.2017.04.004</a></dgdoi:pub-id>
  4. [4] V. Campos, B. Jou, and X. Giró-i-Nieto, “From pixels to sentiment: Fine-tuning CNNs for visual sentiment prediction,” <em>Image and Vision Computing</em>, vol. 65, pp. 15–22, 2017. <ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="<a href="https://doi.org/10.1016/j.imavis.2017.01.011" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">https://doi.org/10.1016/j.imavis.2017.01.011</a>">https://doi.org/10.1016/j.imavis.2017.01.011</ext-link><dgdoi:pub-id xmlns:dgdoi="http://degruyter.com/resources/doi-from-crossref" pub-id-type="doi"><a href="https://doi.org/10.1016/j.imavis.2017.01.011" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">10.1016/j.imavis.2017.01.011</a></dgdoi:pub-id>
  5. [5] L. H. S. Vogado, R. M. S. Veras, F. H. D. Araujo, R. R. V. Silva, and K. R. T. Aires, “Leukemia diagnosis in blood slides using transfer learning in CNNs and SVM for classification,” <em>Engineering Applications of Artificial Intelligence</em>, vol. 72, pp. 415–422, 2018. <ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="<a href="https://doi.org/10.1016/j.engappai.2018.04.024" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">https://doi.org/10.1016/j.engappai.2018.04.024</a>">https://doi.org/10.1016/j.engappai.2018.04.024</ext-link><dgdoi:pub-id xmlns:dgdoi="http://degruyter.com/resources/doi-from-crossref" pub-id-type="doi"><a href="https://doi.org/10.1016/j.engappai.2018.04.024" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">10.1016/j.engappai.2018.04.024</a></dgdoi:pub-id>
  6. [6] A. Khatami, M. Babaie, H. R. Tizhoosh, A. Khosravi, T. Nguyen, and S. Nahavandi, “A sequential search-space shrinking using CNN transfer learning and a Radon projection pool for medical image retrieval,” <em>Expert Systems with Applications</em>, vol. 100, pp. 224–233, 2018. <ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="<a href="https://doi.org/10.1016/j.eswa.2018.01.056" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">https://doi.org/10.1016/j.eswa.2018.01.056</a>">https://doi.org/10.1016/j.eswa.2018.01.056</ext-link><dgdoi:pub-id xmlns:dgdoi="http://degruyter.com/resources/doi-from-crossref" pub-id-type="doi"><a href="https://doi.org/10.1016/j.eswa.2018.01.056" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">10.1016/j.eswa.2018.01.056</a></dgdoi:pub-id>
  7. [7] X. Cheng, J. Lu, J. Feng, B. Yuan, and J. Zhou, “Scene recognition with objectness,” <em>Pattern Recognition</em>, vol. 74, pp. 474–487, 2018. <ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="<a href="https://doi.org/10.1016/j.patcog.2017.09.025" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">https://doi.org/10.1016/j.patcog.2017.09.025</a>">https://doi.org/10.1016/j.patcog.2017.09.025</ext-link><dgdoi:pub-id xmlns:dgdoi="http://degruyter.com/resources/doi-from-crossref" pub-id-type="doi"><a href="https://doi.org/10.1016/j.patcog.2017.09.025" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">10.1016/j.patcog.2017.09.025</a></dgdoi:pub-id>
  8. [8] X. Song, S. Jiang, L. Herranz, Y. Kong, and K. Zheng, “Category co-occurrence modeling for large scale scene recognition,” <em>Pattern Recognition</em>, vol. 59, pp. 98–111, 2016. <ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="<a href="https://doi.org/10.1016/j.patcog.2016.01.019" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">https://doi.org/10.1016/j.patcog.2016.01.019</a>">https://doi.org/10.1016/j.patcog.2016.01.019</ext-link><dgdoi:pub-id xmlns:dgdoi="http://degruyter.com/resources/doi-from-crossref" pub-id-type="doi"><a href="https://doi.org/10.1016/j.patcog.2016.01.019" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">10.1016/j.patcog.2016.01.019</a></dgdoi:pub-id>
  9. [9] S. Gould, R. Fulton, and D. Koller, “Decomposing a scene into geometric and semantically consistent regions,” <em>Proceedings of 2009 IEEE 12th International Conference on Computer Vision</em>, pp. 1–8, 2009. <ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="<a href="https://doi.org/10.1109/iccv.2009.5459211" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">https://doi.org/10.1109/iccv.2009.5459211</a>">https://doi.org/10.1109/iccv.2009.5459211</ext-link><dgdoi:pub-id xmlns:dgdoi="http://degruyter.com/resources/doi-from-crossref" pub-id-type="doi"><a href="https://doi.org/10.1109/ICCV.2009.5459211" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">10.1109/ICCV.2009.5459211</a></dgdoi:pub-id>
  10. [10] Z. Ding, M. Shao, and Y. Fu, “Incomplete multisource transfer learning,” <em>IEEE Transactions on Neural Networks and Learning Systems</em>, vol. 29, no. 2, pp. 310–323, 2018. <ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="<a href="https://doi.org/10.1109/TNNLS.2016.2618765" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">https://doi.org/10.1109/TNNLS.2016.2618765</a>">https://doi.org/10.1109/TNNLS.2016.2618765</ext-link><dgdoi:pub-id xmlns:dgdoi="http://degruyter.com/resources/doi-from-crossref" pub-id-type="doi"><a href="https://doi.org/10.1109/TNNLS.2016.2618765" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">10.1109/TNNLS.2016.2618765</a></dgdoi:pub-id><dgpm:pub-id xmlns:dgpm="http://degruyter.com/resources/fetched-pubmed-id" pub-id-type="pmid">28113958</dgpm:pub-id>
  11. [11] H. Zhao, Q. Liu, and Y. Yang, “Transfer learning with ensemble of multiple feature representations,” <em>Proceedings of 2018 IEEE 16th International Conference on Software Engineering Research, Management and Applications (SERA)</em>, pp. 54–61, 2018. <ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="http://doi.ieeecomputersociety.org/<a href="https://doi.org/10.1109/SERA.2018.8477189" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">10.1109/SERA.2018.8477189</a>">http://doi.ieeecomputersociety.org/<a href="https://doi.org/10.1109/SERA.2018.8477189" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">10.1109/SERA.2018.8477189</a></ext-link><dgdoi:pub-id xmlns:dgdoi="http://degruyter.com/resources/doi-from-crossref" pub-id-type="doi"><a href="https://doi.org/10.1109/SERA.2018.8477189" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">10.1109/SERA.2018.8477189</a></dgdoi:pub-id>
  12. [12] H. Azizpour, A. S. Razavian, J. Sullivan, A. Maki, and S. Carlsson, “Factors of transferability for a generic ConvNet representation,” <em>IEEE Transactions on Pattern Analysis and Machine Intelligence</em>, vol. 38, no. 9, pp. 1790–1802, 2016. <ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="<a href="https://doi.org/10.1109/TPAMI.2015.2500224" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">https://doi.org/10.1109/TPAMI.2015.2500224</a>">https://doi.org/10.1109/TPAMI.2015.2500224</ext-link><dgdoi:pub-id xmlns:dgdoi="http://degruyter.com/resources/doi-from-crossref" pub-id-type="doi"><a href="https://doi.org/10.1109/TPAMI.2015.2500224" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">10.1109/TPAMI.2015.2500224</a></dgdoi:pub-id><dgpm:pub-id xmlns:dgpm="http://degruyter.com/resources/fetched-pubmed-id" pub-id-type="pmid">26584488</dgpm:pub-id>
  13. [13] S. Bai, and H. Tang, “Softly combining an ensemble of classifiers learned from a single convolutional neural network for scene categorization,” <em>Applied Soft Computing</em>, vol. 67, pp. 183–196, 2018. <ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="<a href="https://doi.org/10.1016/j.asoc.2018.03.007" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">https://doi.org/10.1016/j.asoc.2018.03.007</a>">https://doi.org/10.1016/j.asoc.2018.03.007</ext-link><dgdoi:pub-id xmlns:dgdoi="http://degruyter.com/resources/doi-from-crossref" pub-id-type="doi"><a href="https://doi.org/10.1016/j.asoc.2018.03.007" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">10.1016/j.asoc.2018.03.007</a></dgdoi:pub-id>
  14. [14] P. Tang, H. Wang, and S. Kwong, “G-MS2F: GoogLeNet based multi-stage feature fusion of deep CNN for scene recognition,” <em>Neurocomputing</em>, vol. 225, pp. 188–197, 2017. <ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="<a href="https://doi.org/10.1016/j.neucom.2016.11.023" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">https://doi.org/10.1016/j.neucom.2016.11.023</a>">https://doi.org/10.1016/j.neucom.2016.11.023</ext-link><dgdoi:pub-id xmlns:dgdoi="http://degruyter.com/resources/doi-from-crossref" pub-id-type="doi"><a href="https://doi.org/10.1016/j.neucom.2016.11.023" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">10.1016/j.neucom.2016.11.023</a></dgdoi:pub-id>
  15. [15] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” <em>Communications of the ACM</em>, vol. 60, no. 2, pp. 84–90, 2017. <ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="<a href="https://doi.org/10.1145/3065386" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">https://doi.org/10.1145/3065386</a>">https://doi.org/10.1145/3065386</ext-link><dgdoi:pub-id xmlns:dgdoi="http://degruyter.com/resources/doi-from-crossref" pub-id-type="doi"><a href="https://doi.org/10.1145/3065386" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">10.1145/3065386</a></dgdoi:pub-id>
  16. [16] C. Wang, J. Yu, and D. Tao, “High-level attributes modeling for indoor scenes classification,” <em>Neurocomputing</em>, vol. 121, pp. 337–343, 2013. <ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="<a href="https://doi.org/10.1016/j.neucom.2013.05.032" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">https://doi.org/10.1016/j.neucom.2013.05.032</a>">https://doi.org/10.1016/j.neucom.2013.05.032</ext-link><dgdoi:pub-id xmlns:dgdoi="http://degruyter.com/resources/doi-from-crossref" pub-id-type="doi"><a href="https://doi.org/10.1016/j.neucom.2013.05.032" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">10.1016/j.neucom.2013.05.032</a></dgdoi:pub-id>
  17. [17] S. Bai, “Growing random forest on deep convolutional neural networks for scene categorization,” <em>Expert Systems with Applications</em>, vol. 71, pp. 279–287, 2017. <ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="<a href="https://doi.org/10.1016/j.eswa.2016.10.038" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">https://doi.org/10.1016/j.eswa.2016.10.038</a>">https://doi.org/10.1016/j.eswa.2016.10.038</ext-link><dgdoi:pub-id xmlns:dgdoi="http://degruyter.com/resources/doi-from-crossref" pub-id-type="doi"><a href="https://doi.org/10.1016/j.eswa.2016.10.038" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">10.1016/j.eswa.2016.10.038</a></dgdoi:pub-id>
  18. [18] B.-J. Han, and J.-Y. Sim, “Saliency detection for panoramic landscape images of outdoor scenes,” <em>Journal of Visual Communication and Image Representation</em>, vol. 49, pp. 27–37, 2017. <ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="<a href="https://doi.org/10.1016/j.jvcir.2017.08.003" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">https://doi.org/10.1016/j.jvcir.2017.08.003</a>">https://doi.org/10.1016/j.jvcir.2017.08.003</ext-link><dgdoi:pub-id xmlns:dgdoi="http://degruyter.com/resources/doi-from-crossref" pub-id-type="doi"><a href="https://doi.org/10.1016/j.jvcir.2017.08.003" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">10.1016/j.jvcir.2017.08.003</a></dgdoi:pub-id>
  19. [19] J.-T. Lee, H.-U. Kim, C. Lee, and C.-S. Kim, “Photographic composition classification and dominant geometric element detection for outdoor scenes,” <em>Journal of Visual Communication and Image Representation</em>, vol. 55, pp. 91–105, 2018. <ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="<a href="https://doi.org/10.1016/j.jvcir.2018.05.018" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">https://doi.org/10.1016/j.jvcir.2018.05.018</a>">https://doi.org/10.1016/j.jvcir.2018.05.018</ext-link><dgdoi:pub-id xmlns:dgdoi="http://degruyter.com/resources/doi-from-crossref" pub-id-type="doi"><a href="https://doi.org/10.1016/j.jvcir.2018.05.018" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">10.1016/j.jvcir.2018.05.018</a></dgdoi:pub-id>
  20. [20] B. Liu, S. Gould, and D. Koller, “Single image depth estimation from predicted semantic labels,” <em>Proceedings of 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition</em>, pp. 1253–1260, 2010. <ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="<a href="https://doi.org/10.1109/cvpr.2010.5539823" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">https://doi.org/10.1109/cvpr.2010.5539823</a>">https://doi.org/10.1109/cvpr.2010.5539823</ext-link><dgdoi:pub-id xmlns:dgdoi="http://degruyter.com/resources/doi-from-crossref" pub-id-type="doi"><a href="https://doi.org/10.1109/CVPR.2010.5539823" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">10.1109/CVPR.2010.5539823</a></dgdoi:pub-id>
  21. [21] V. V. Romanuke, “Appropriate number and allocation of ReLUs in convolutional neural networks,” <em>Research Bulletin of the National Technical University of Ukraine “Kyiv Polytechnic Institute”</em>, no. 1, pp. 69–78, 2017. <ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="<a href="https://doi.org/10.20535/1810-0546.2017.1.88156" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">https://doi.org/10.20535/1810-0546.2017.1.88156</a>">https://doi.org/10.20535/1810-0546.2017.1.88156</ext-link><dgdoi:pub-id xmlns:dgdoi="http://degruyter.com/resources/doi-from-crossref" pub-id-type="doi"><a href="https://doi.org/10.20535/1810-0546.2017.1.88156" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">10.20535/1810-0546.2017.1.88156</a></dgdoi:pub-id>
  22. [22] V. Romanuke, “Optimal training parameters and hidden layer neuron number of two-layer perceptron for generalised scaled object classification problem,” <em>Information Technology and Management Science</em>, vol. 18, no. 1, pp. 42–48, 2015. <ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="<a href="https://doi.org/10.1515/itms-2015-0007" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">https://doi.org/10.1515/itms-2015-0007</a>">https://doi.org/10.1515/itms-2015-0007</ext-link><dgdoi:pub-id xmlns:dgdoi="http://degruyter.com/resources/doi-from-crossref" pub-id-type="doi"><a href="https://doi.org/10.1515/itms-2015-0007" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">10.1515/itms-2015-0007</a></dgdoi:pub-id>
  23. [23] V. V. Romanuke, “Interval uncertainty reduction via division-by-2 dichotomization based on expert estimations for short-termed observations,” <em>Journal of Uncertain Systems</em>, vol. 1, no. 12, pp. 3–21, 2018.
  24. [24] J. Yang, S. Li, and W. Xu, “An iterative transfer learning based classification framework,” <em>Proceedings of 2018 International Joint Conference on Neural Networks (IJCNN)</em>, pp. 1–8, 2018. <ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="<a href="https://doi.org/10.1109/IJCNN.2018.8489471" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">https://doi.org/10.1109/IJCNN.2018.8489471</a>">https://doi.org/10.1109/IJCNN.2018.8489471</ext-link><dgdoi:pub-id xmlns:dgdoi="http://degruyter.com/resources/doi-from-crossref" pub-id-type="doi"><a href="https://doi.org/10.1109/IJCNN.2018.8489471" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">10.1109/IJCNN.2018.8489471</a></dgdoi:pub-id>
  25. [25] X. Liu, Z. Liu, G. Wang, Z. Cai, and H. Zhang, “Ensemble transfer learning algorithm,” <em>IEEE Access</em>, vol. 6, pp. 2389–2396, 2018. <ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="<a href="https://doi.org/10.1109/ACCESS.2017.2782884" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">https://doi.org/10.1109/ACCESS.2017.2782884</a>">https://doi.org/10.1109/ACCESS.2017.2782884</ext-link><dgdoi:pub-id xmlns:dgdoi="http://degruyter.com/resources/doi-from-crossref" pub-id-type="doi"><a href="https://doi.org/10.1109/ACCESS.2017.2782884" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">10.1109/ACCESS.2017.2782884</a></dgdoi:pub-id>
  26. [26] Y. Liu, D. Yang, and C. Zhang, “Relaxed conditions for convergence analysis of online back-propagation algorithm with regularizer for Sigma-Pi-Sigma neural network,” <em>Neurocomputing</em>, vol. 272, pp. 163–169, 2018. <ext-link ext-link-type="uri" xmlns:xlink="http://www.w3.org/1999/xlink" xlink:href="<a href="https://doi.org/10.1016/j.neucom.2017.06.057" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">https://doi.org/10.1016/j.neucom.2017.06.057</a>">https://doi.org/10.1016/j.neucom.2017.06.057</ext-link><dgdoi:pub-id xmlns:dgdoi="http://degruyter.com/resources/doi-from-crossref" pub-id-type="doi"><a href="https://doi.org/10.1016/j.neucom.2017.06.057" target="_blank" rel="noopener noreferrer" class="text-signal-blue hover:underline">10.1016/j.neucom.2017.06.057</a></dgdoi:pub-id>
DOI: https://doi.org/10.2478/acss-2018-0018 | Journal eISSN: 2255-8691 | Journal ISSN: 2255-8683
Language: English
Page range: 141 - 149
Published on: Dec 31, 2018
Published by: Riga Technical University
In partnership with: Paradigm Publishing Services
Publication frequency: 1 times per year

© 2018 Vadim Romanuke, published by Riga Technical University
This work is licensed under the Creative Commons Attribution 4.0 License.