Abstract
Recently, Spiking Neural Networks (SNNs) have been considered as alternatives to the common deep neural networks (DNNs) when the energy efficiency has been targeted. The SNNs adopt an event-driven information processing approach in which the computational expenses are reduced considerably compared to DNNs without affecting the system performance. This paper presents an efficient framework based on SNNs for touch modality classification. The proposed work outperforms similar state of the art solutions by achieving a classification accuracy of 99.97% with decreased complexity and increased number of classes.
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
References
Dahiya, R.S., Metta, G., Valle, M., Sandini, G.: Tactile sensing-from humans to humanoids. IEEE Trans. Rob. 26(1), 1–20 (2009)
VanRullen, R., Guyonneau, R., Thorpe, S.J.: Spike times make sense. Trends Neurosci. 28(1), 1–4 (2005)
Maass, W.: Networks of spiking neurons: the third generation of neural network models. Neural Netw. 10(9), 1659–1671 (1997)
Gütig, R., Sompolinsky, H.: The tempotron: a neuron that learns spike timing-based decisions. Nat. Neurosci. 9(3), 420–428 (2006)
Bologna, L.L., Pinoteau, J., Brasselet, R., Maggiali, M., Arleo, A.: Encoding/decoding of first and second order tactile afferents in a neurorobotic application. J. Physiol. Paris 105(1–3), 25–35 (2011)
Gütig, R., Gollisch, T., Sompolinsky, H., Meister, M.: Computing complex visual features with retinal spike times. PLoS ONE 8(1), e53063 (2013)
Nessler, B., Pfeiffer, M., Maass, W.: Stdp enables spiking neurons to detect hidden causes of their inputs. Adv. Neural. Inf. Process. Syst. 22, 1357–1365 (2009)
Legenstein, R., Pecevski, D., Maass, W.: A learning theory for reward-modulated spike-timing-dependent plasticity with application to biofeedback. PLoS Comput. Biol. 4(10), e1000180 (2008)
Schrauwen, B., D’Haene, M., Verstraeten, D., Van Campenhout, J.: Compact hardware liquid state machines on fpga for real-time speech recognition. Neural Netw. 21(2–3), 511–523 (2008)
Rice, K.L., Bhuiyan, M.A., Taha, T.M., Vutsinas, C.N., Smith, M.C.: Fpga implementation of izhikevich spiking neural networks for character recognition. In: 2009 International Conference on Reconfigurable Computing and FPGAs, pp. 451–456. IEEE (2009)
Gütig, R.: To spike, or when to spike? Curr. Opin. Neurobiol. 25, 134–139 (2014)
Talbot, M., Arvandi, M., Sadeghian, A.: A neural network based surface roughness discrimination algorithm. In: 2008 World Automation Congress, pp. 1–8. IEEE (2008)
Decherchi, S., Gastaldo, P., Dahiya, R.S., Valle, M., Zunino, R.: Tactile-data classification of contact materials using computational intelligence. IEEE Trans. Rob. 27(3), 635–639 (2011)
Dabbous, A., Mastella, M., Natarajan, A., Chicca, E., Valle, M., Bartolozzi, C.: Artificial bio-inspired tactile receptive fields for edge orientation classification. In: 2021 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1–5. IEEE (2021)
Kim, J., et al.: Object shape recognition using tactile sensor arrays by a spiking neural network with unsupervised learning. In: 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 178–183. IEEE (2020)
Iwata, H., Sugano, S.: Human-robot-contact-state identification based on tactile recognition. IEEE Trans. Industr. Electron. 52(6), 1468–1477 (2005)
Stiehl, W.D., Breazeal, C.: Applying a “somatic alphabet” approach to inferring orientation, motion, and direction in clusters of force sensing resistors. In: 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No. 04CH37566), vol. 3, pp. 3015–3020. IEEE (2004)
Gianoglio, C., Ragusa, E., Zunino, R., Valle, M.: 1-d convolutional neural networks for touch modalities classification. In: 2021 28th IEEE International Conference on Electronics, Circuits, and Systems (ICECS), pp. 1–6. IEEE (2021)
Gianoglio, C., Ragusa, E., Gastaldo, P., Valle, M.: A novel learning strategy for the trade-off between accuracy and computational cost: a touch modalities classification case study. IEEE Sens. J. 22(1), 659–670 (2021)
Sun, J., Billing, E., Seoane, F., Zhou, B., Högberg, D., Hemeren, P.: Categories of touch: classifying human touch using a soft tactile sensor. In: The robotic sense of touch: From sensing to understanding, workshop at the IEEE International Conference on Robotics and Automation (ICRA), Singapore, 29 May 2017 (2017)
Dabbous, A., Ibrahim, A., Valle, M., Bartolozzi, C.: Touch modality classification using spiking neural networks and supervised-stdp learning. In: 2021 28th IEEE International Conference on Electronics, Circuits, and Systems (ICECS), pp. 1–4. IEEE
Stimberg, M., Brette, R., Goodman, D.F.: Brian 2, an intuitive and efficient neural simulator. eLife 8, e47314 (2019)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Dabbous, A., Ibrahim, A., Valle, M. (2023). Feed-Forward SNN for Touch Modality Prediction. In: Valle, M., et al. Advances in System-Integrated Intelligence. SYSINT 2022. Lecture Notes in Networks and Systems, vol 546. Springer, Cham. https://doi.org/10.1007/978-3-031-16281-7_21
Download citation
DOI: https://doi.org/10.1007/978-3-031-16281-7_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16280-0
Online ISBN: 978-3-031-16281-7
eBook Packages: EngineeringEngineering (R0)