Abstract
Recurrent neural networks are a powerful means in diverse applications. We show that, together with so-called conceptors, they also allow fast learning, in contrast to other deep learning methods. In addition, a relatively small number of examples suffices to train neural networks with high accuracy. We demonstrate this with two applications, namely speech recognition and detecting car driving maneuvers. We improve the state of the art by application-specific preparation techniques: For speech recognition, we use mel frequency cepstral coefficients leading to a compact representation of the frequency spectra, and detecting car driving maneuvers can be done without the commonly used polynomial interpolation, as our evaluation suggests.
Keywords
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Clopper, C.G., Pisoni, D.B., Tierney, A.T.: Effects of open-set and closed-set task demands on spoken word recognition. J. Am. Acad. Audiol. 17(5), 331–349 (2006). http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3324094/
Deng, L., Yu, D.: Deep learning: Methods and applications. Found. Trends Sign. Process. 7(3–4), 198–387 (2014). http://research.microsoft.com/pubs/209355/DeepLearning-NowPublishing-Vol7-SIG-039.pdf
Dey, N.: Intelligent Speech Signal Processing. Academic Press, Cambridge (2019)
He, X., Jaeger, H.: Overcoming catastrophic interference using conceptor-aided backpropagation. In: ICLR 2018 – 6th International Conference on Learning Representations. Vancouver (2018). arXiv:1707.04853
Hong, J.H., Margines, B., Dey, A.K.: A smartphone-based sensing platform to model aggressive driving behaviors. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pp. 4047–4056. CHI 2014, ACM, New York, NY, USA (2014). https://doi.org/10.1145/2556288.2557321
Ibrahim, Y.A., Odiketa, J.C., Ibiyemi, T.S.: Preprocessing technique in automatic speech recognition for human computer interaction: an overview. Ann. Comput. Sci. Ser. 15(1), 186–191 (2017)
Islinger, T., Köhler, T., Ludwig, B.: Driver distraction analysis based on FFT of steering wheel angle. In: Adjunct Proceedings of the 3rd International Conference on Automotive User Interfaces and Interactive Vehicular Applications, pp. 21–22 (2011). http://www.auto-ui.org/11/docs/AUI2011_adjunctproceedings.pdf
Jaeger, H.: Echo state network. Scholarpedia 2(9), 2330 (2007). https://doi.org/10.4249/scholarpedia.2330, revision #151757
Jaeger, H.: Controlling recurrent neural networks by conceptors. CoRR - computing research repository, Cornell University Library (2014). arXiv:1403.3369
Jaeger, H.: Using conceptors to manage neural long-term memories for temporal patterns. J. Mach. Learn. Res. 18(1), 387–429 (2017). https://doi.org/10.5555/3122009.3122022
Jaeger, H., Haas, H.: Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication. Science 304(5667), 78–80 (2004)
Otto, O.: Analysis of smartphone sensor data with recurrent neural networks for classification of driving maneuvers. WAIT 03/2020, Automation and Computer Sciences Department, Harz University of Applied Sciences (2020). https://doi.org/10.25673/35931, in German
Pawara, P., Okafor, E., Groefsema, M., He, S., Schomaker, L.R., Wiering, M.A.: One-vs-one classification for deep neural networks. Pattern Recogn. 108, 107528 (2020). https://doi.org/10.1016/j.patcog.2020.107528
Stolzenburg, F., Litz, S., Michael, O., Obst, O.: The power of linear recurrent neural networks. CoRR – computing research repository, Cornell University Library (2018). arXiv:1802.03308, latest revision 2021
Torkkola, K., Massey, N., Wood, C.: Driver inattention detection through intelligent analysis of readily available sensors. In: Proceedings of 7th International IEEE Conference on Intelligent Transportation Systems (IEEE Cat. No.04TH8749), pp. 326–331 (2004). https://doi.org/10.1109/ITSC.2004.1398919
Vaiana, R., Iuele, T., Astarita, V., Caruso, M.V., Tassitani, A., Zaffino, C., Giofré, V.: Driving behavior and traffic safety: an acceleration-based safety evaluation procedure for smartphones. Mod. Appl. Sci. 8(1), 88–96 (2014). https://doi.org/10.5539/mas.v8n1p88
Warden, P.: Speech commands: A dataset for limited-vocabulary speech recognition. CoRR – computing research repository, Cornell University Library (2018). arXiv:1804.03209
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Krause, S., Otto, O., Stolzenburg, F. (2021). Fast Classification Learning with Neural Networks and Conceptors for Speech Recognition and Car Driving Maneuvers. In: Chomphuwiset, P., Kim, J., Pawara, P. (eds) Multi-disciplinary Trends in Artificial Intelligence. MIWAI 2021. Lecture Notes in Computer Science(), vol 12832. Springer, Cham. https://doi.org/10.1007/978-3-030-80253-0_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-80253-0_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-80252-3
Online ISBN: 978-3-030-80253-0
eBook Packages: Computer ScienceComputer Science (R0)