Abstract
Algorithms in machine learning commonly require training data to be independent and identically distributed. This assumption is not always valid, e. g. in online learning, when data becomes available in homogeneously labeled blocks, which can severely impede especially instance-based learning algorithms. In this work, we analyze and visualize this issue, and we propose and evaluate strategies for Learning Vector Quantization to compensate for homogeneously labeled blocks. We achieve considerably improved results in this difficult setting.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
This strategy is similar to Experience Replay [1] used in Reinforcement Learning.
References
Adam, S., Busoniu, L., Babuska, R.: Experience replay for real-time reinforcement learning control Part C (Appl. Rev.). IEEE Trans. Syst. Man. Cybern. 42(2), 201–212 (2011)
Göpfert, J.P., Hammer, B., Wersing, H.: Mitigating concept drift via rejection. In: Kůrková, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds.) ICANN 2018. LNCS, vol. 11139, pp. 456–467. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01418-6_45
Huang, J., Smola, A.J., Gretton, A., Borgwardt, K.M., Schölkopf, B.: Correcting sample selection bias by unlabeled data. In: NIPS (2006)
Kirstein, S., Wersing, H., Körner, E.: A biologically motivated visual memory architecture for online learning of objects. Neural Netw. 21(1), 65–77 (2008)
Kohonen, T.: Learning Vector quantization. In: Self-Organizing Maps. Springer Series in Information Sciences, vol. 30, pp. 175–189. Springer, Heidelberg (1995). https://doi.org/10.1007/978-3-642-97610-0_6
Krizhevsky, A., Hinton, G., et al.: Learning multiple layers of features from tiny images (2009)
Limberg, C.: CUPSNBOTTLES (2020). https://doi.org/10.21227/ywwz-cb26
Limberg, C., Krieger, K., Wersing, H., Ritter, H.: Active learning for image recognition using a visualization-based user interface. In: Tetko, I.V., Kůrková, V., Karpov, P., Theis, F. (eds.) ICANN 2019. LNCS, vol. 11728, pp. 495–506. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30484-3_40
Limberg, C., Wersing, H., Ritter, H.: Improving active learning by avoiding ambiguous samples. In: Kůrková, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds.) ICANN 2018. LNCS, vol. 11139, pp. 518–527. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01418-6_51
Limberg, C., Wersing, H., Ritter, H.J.: Efficient accuracy estimation for instance-based incremental active learning. In: European Symposium on Artificial Neural Networks (ESANN), pp. 171–176, April 2018
Losing, V., Hammer, B., Wersing, H.: Interactive online learning for obstacle classification on a mobile robot. In: International Joint Conference on Neural Networks (IJCNN) pp. 1–8 (2015)
Losing, V., Hammer, B., Wersing, H.: Incremental on-line learning: a review and comparison of state of the art algorithms. Neurocomputing 275, 1261–1274 (2018)
Sato, A., Yamada, K.: Generalized learning vector quantization. In: proceedings NIPS, pp. 423–429, (1995)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2014). arXiv: 1409.1556
Xiao, H., Rasul, K., Vollgraf, R.: Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747 (2017)
Zhang, J., Wu, X., Sheng, V.S.: Learning from crowdsourced labeled data: a survey. Artif. Intell. Rev. 46(4), 543–576 (2016). https://doi.org/10.1007/s10462-016-9491-9
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Limberg, C., Göpfert, J.P., Wersing, H., Ritter, H. (2020). Prototype-Based Online Learning on Homogeneously Labeled Streaming Data. In: Farkaš, I., Masulli, P., Wermter, S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2020. ICANN 2020. Lecture Notes in Computer Science(), vol 12397. Springer, Cham. https://doi.org/10.1007/978-3-030-61616-8_17
Download citation
DOI: https://doi.org/10.1007/978-3-030-61616-8_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61615-1
Online ISBN: 978-3-030-61616-8
eBook Packages: Computer ScienceComputer Science (R0)