Abstract
Power error loss (PEL) has recently been suggested as a more efficient generalization of binary or categorical cross entropy (BCE/CCE). However, as PEL requires to adapt the exponent q of a power function to training data and learning progress, it has been argued that the observed improvements may be due to implicitly optimizing learning rate. Here we invalidate this argument by optimizing learning rate in each training step. We find that PEL clearly remains superior over BCE/CCE if q is properly decreased during learning. This proves that the dominant mechanism of PEL is better adapting to output error distributions, rather than implicitly manipulating learning rate.
This work was supported by the Ministerium für Wirtschaft, Arbeit und Tourismus Baden-Württemberg (VwV Invest BW - Innovation) via the project KICAD (FKZ BW1_0092/02) and by the Deutsches Bundesministerium für Verkehr und digitale Infrastruktur (Modernitätsfonds/mFUND) via the project AI4Infra (FKZ 19F2112C). The author acknowledges support by the state of Baden-Württemberg through bwHPC. The author is also grateful to German Nemirovski, Rober Frank, and Lukas Lorek for valuable discussions and help with the computing infrastructure.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw. 5(2), 157–166 (1994)
Bishop, C.: Pattern Recognition and Machine Learning. Springer, New York (2006)
Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Proceedings of the European Conference on Computer Vision (ECCV). arXiv preprint arXiv:1802.02611v2 (2018)
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Teh, Y., Titterington, M. (eds.) Proceedings of the 13th International Conference on Artificial Intelligence and Statistics, Proceedings of Machine Learning Research, vol. 9, pp. 249–256. JMLR Workshop and Conference Proceedings, Chia Laguna Resort, Sardinia, Italy (2010)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016). http://www.deeplearningbook.org
He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), December 2015
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, 27–30 June 2016, pp. 770–778. IEEE Computer Society (2016). https://doi.org/10.1109/CVPR.2016.90
Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd Proceedings of the International Conference on Learning Representations (ICLR). arXiv:1412.6980v9 (2015)
Knoblauch, A.: Power function error initialization can improve convergence of backpropagation learning in neural networks for classification. Neural Comput. 33(8), 2193–2225 (2021)
Knoblauch, A.: On the antiderivatives of \(x^p/(1-x)\) with an application to optimize loss functions for classification with neural networks. Ann. Math. Artif. Intell. 90(4), 425–452 (2022)
Knoblauch, A., Luniak, P.: Improving learning of neural networks for classification, segmentation, and associative memory. In: Proceedings of the 7th bwHPC Symposium, 8 November 2021, Ulm, Germany (2022, to appear)
Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. In: Pereira, F., Burges, C., Bottou, L., Weinberger, K. (eds.) Advances in Neural Information Processing Systems, vol. 25. Curran Associates, Inc. (2012)
Krizhevsky, A.: Learning multiple layers of features from tiny images. Technical report, Department of Computer Science, University of Toronto (2009)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Ruder, S.: An overview of gradient descent optimization algorithms. arXiv preprint arXiv:1609.04747 (2016)
Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85–117 (2015)
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(56), 1929–1958 (2014)
Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: Chaudhuri, K., Salakhutdinov, R. (eds.) Proceedings of the 36th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 97, pp. 6105–6114. PMLR, 09–15 June 2019
Werbos, P.J.: Beyond regression: new tools for prediction and analysis in the behavioral sciences. Ph.D. thesis, Harvard University (1974)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Knoblauch, A. (2022). Adapting Loss Functions to Learning Progress Improves Accuracy of Classification in Neural Networks. In: Ceci, M., Flesca, S., Masciari, E., Manco, G., Raś, Z.W. (eds) Foundations of Intelligent Systems. ISMIS 2022. Lecture Notes in Computer Science(), vol 13515. Springer, Cham. https://doi.org/10.1007/978-3-031-16564-1_26
Download citation
DOI: https://doi.org/10.1007/978-3-031-16564-1_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16563-4
Online ISBN: 978-3-031-16564-1
eBook Packages: Computer ScienceComputer Science (R0)