Skip to main content

Advertisement

Springer Nature Link
Log in

RD-NMSVM: neural mapping support vector machine based on parameter regularization and knowledge distillation

  • Original Article
  • Published:
International Journal of Machine Learning and Cybernetics Aims and scope Submit manuscript

Abstract

Artificial neural networks (ANNs) model has made remarkable achievements in many fields. Therefore, we have greater expectation for it, expecting it to have the same intelligence as human beings. However, ANNs still can’t perform continual learning like humans at present. The serious defect of ANNs model is called the catastrophic forgetting problem. For this problem, we put forward a novel method called neural mapping support vector machine based on Parameter Regularization and Knowledge Distillation or RD-NMSVM for short. Our model consists of three parts: firstly, the shared neural network module, which is used to extract common features of different tasks; Secondly, the specific task module, which employs multi-classification support vector machine as classifier, and it is equivalent to using neural networks as neural kernel mapping of support vector machine; Thirdly, the parameter regularization and knowledge distillation module, which inhibits the parameters of the shared network module from updating greatly and learns previous knowledge. Note that RD-NMSVM doesn’t utilize samples of previous tasks. From our experiments, we can see that RD-NMSVM has obvious advantages in eliminating catastrophic forgetting of ANNs model.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Explore related subjects

Discover the latest articles and news from researchers in related subjects, suggested using machine learning.

References

  1. Zhou T, Li Z, Zhang C (2019) Enhance the recognition ability to occlusions and small objects with Robust Faster R-CNN. Int J Mach Learn Cybern 10:3155–3166. https://doi.org/10.1007/s13042-019-01006-4

    Article  Google Scholar 

  2. Chen H, Yao M, Gu Q (2020) Pothole detection using location-aware convolutional neural networks. Int J Mach Learn Cybern 11:899–911. https://doi.org/10.1007/s13042-020-01078-7

    Article  Google Scholar 

  3. Lin Y, Li Q, Yang B et al (2021) Improving speech recognition models with small samples for air traffic control systems. Neurocomputing 445:287–297. https://doi.org/10.1016/j.neucom.2020.08.092

    Article  Google Scholar 

  4. Moritz N, Hori T, Roux J Le (2020) Streaming automatic speech recognition with the transformer model. In: Proceedings of ICASSP, IEEE Int Conf Acoust Speech Signal Process. 2020-May. pp 6074–6078. https://doi.org/10.1109/ICASSP40776.2020.9054476

  5. Bi JW, Liu Y, Fan ZP (2020) A deep neural networks based recommendation algorithm using user and item basic data. Int J Mach Learn Cybern 11:763–777. https://doi.org/10.1007/s13042-019-00981-y

    Article  Google Scholar 

  6. Qian F, Huang Y, Li J et al (2021) DLSA: dual-learning based on self-attention for rating prediction. Int J Mach Learn Cybern 12:1993–2005. https://doi.org/10.1007/s13042-021-01288-7

    Article  Google Scholar 

  7. Zhao K, Jiang H, Li X, Wang R (2021) Ensemble adaptive convolutional neural networks with parameter transfer for rotating machinery fault diagnosis. Int J Mach Learn Cybern 12:1483–1499. https://doi.org/10.1007/s13042-020-01249-6

    Article  Google Scholar 

  8. Ye T, Zhang Z, Zhang X et al (2021) Fault detection of railway freight cars mechanical components based on multi-feature fusion convolutional neural network. Int J Mach Learn Cybern 12:1789–1801. https://doi.org/10.1007/s13042-021-01274-z

    Article  Google Scholar 

  9. Hsu M-F, Lin S-J (2021) A BSC-based network DEA model equipped with computational linguistics for performance assessment and improvement. Int J Mach Learn Cybern 12:2479–2497. https://doi.org/10.1007/s13042-021-01331-7

    Article  Google Scholar 

  10. Suri JS, Puvvula A, Majhail M et al (2020) Integration of cardiovascular risk assessment with COVID-19 using artificial intelligence. Rev Cardiovasc Med 21:541–560. https://doi.org/10.31083/j.rcm.2020.04.236

    Article  Google Scholar 

  11. Sung I, Choi B, Nielsen P (2021) On the training of a neural network for online path planning with offline path planning algorithms. Int J Inf Manag 57:102142. https://doi.org/10.1016/j.ijinfomgt.2020.102142

    Article  Google Scholar 

  12. Yan C, Xiang X, Wang C (2020) Towards real-time path planning through deep reinforcement learning for a UAV in dynamic environments. J Intell Robot Syst 98:297–309. https://doi.org/10.1007/s10846-019-01073-3

    Article  Google Scholar 

  13. Castrejón L, Kundu K, Urtasun R, Fidler S (2017) Annotating object instances with a polygon-RNN. In: Proceedings: 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017. pp 4485–4493

  14. Zheng S, Jayasumana S, Romera-Paredes B et al (2015) Conditional random fields as recurrent neural networks. In: Proceedings of IEEE Int Conf Comput Vis 2015 Inter. pp 1529–1537. https://doi.org/10.1109/ICCV.2015.179

  15. Visin F, Romero A, Cho K et al (2016) ReSeg: a recurrent neural network-based model for semantic segmentation. IEEE Comput Soc Conf Comput Vis Pattern Recognit Work. https://doi.org/10.1109/CVPRW.2016.60

    Article  Google Scholar 

  16. Luo J, Wu J, Zhao S et al (2019) Lossless compression for hyperspectral image using deep recurrent neural networks. Int J Mach Learn Cybern 10:2619–2629. https://doi.org/10.1007/s13042-019-00937-2

    Article  Google Scholar 

  17. Chen J, Yang L, Zhang Y et al (2016) Combining fully convolutional and recurrent neural networks for 3d biomedical image segmentation. In: Advances in neural information processing systems. pp 3036–3044

  18. Vaswani A, Shazeer N, Parmar N et al (2017) Attention is all you need. In: Advances in neural information processing systems. pp 5998–6008

  19. Zheng S, Lu J, Zhao H et al (2021) Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp 6881–6890

  20. Dai Z, Cai B, Lin Y, Chen J (2021) Up-detr: Unsupervised pre-training for object detection with transformers. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp 1601–1610

  21. Tan F, Kong Y, Fan Y, et al (2021) SDNet: mutil-branch for single image deraining using swin. arXiv Prepr. http://arxiv.org/abs/2105.15077

  22. Chen H, Wang Y, Guo T et al (2021) Pre-trained image processing transformer. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp 12299–12310

  23. Guo S, Yan Z, Zhang K et al (2019) Toward convolutional blind denoising of real photographs. In: Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit 2019-June. pp. 1712–1722. https://doi.org/10.1109/CVPR.2019.00181

  24. Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells WM, Frangi AF (eds) Medical image computing and computer-assisted intervention—MICCAI 2015. Springer International Publishing, Cham, pp 234–241

    Chapter  Google Scholar 

  25. Liu B, Zhou Y, Sun W (2020) Character-level text classification via convolutional neural network and gated recurrent unit. Int J Mach Learn Cybern 11:1939–1949. https://doi.org/10.1007/s13042-020-01084-9

    Article  Google Scholar 

  26. Hajiabadi H, Molla-Aliod D, Monsefi R, Yazdi HS (2020) Combination of loss functions for deep text classification. Int J Mach Learn Cybern 11:751–761. https://doi.org/10.1007/s13042-019-00982-x

    Article  Google Scholar 

  27. Gehring J, Auli M, Grangier D et al (2017) Convolutional sequence to sequence learning. In: International conference on machine learning. PMLR, pp 1243–1252

  28. Wang S, Wang B, Gong J et al (2020) Combining ResNet and transformer for Chinese grammatical error diagnosis. In: Proc 6th Work Nat Lang Process Tech Educ Appl, pp 36–43

  29. Grossberg S (1982) Studies of mind and brain: neural principles of learning, perception, development, cognition, and motor control. Bost Stud Philos Sci xvii:662

    MATH  Google Scholar 

  30. Parisi GI, Kemker R, Part JL et al (2019) Continual lifelong learning with neural networks: a review. Neural Netw 113:54–71. https://doi.org/10.1016/j.neunet.2019.01.012

    Article  Google Scholar 

  31. Rannen A, Aljundi R, Blaschko MB, Tuytelaars T (2017) Encoder based lifelong learning. In: 2017 IEEE international conference on computer vision (ICCV). pp 1329–1337

  32. Farajtabar M, Azizan N, Mott A, Li A (2020) Orthogonal Gradient Descent for Continual Learning. In: Chiappa S, Calandra R (eds) Proceedings of the twenty third international conference on artificial intelligence and statistics. PMLR, pp 3762–3773

  33. Zenke F, Poole B, Ganguli S (2017) Continual Learning Through Synaptic Intelligence. In: Precup D, Teh YW (eds) Proceedings of the 34th international conference on machine learning. PMLR, pp 3987–3995

  34. Isele D, Cosgun A (2018) Selective experience replay for lifelong learning. Proc AAAI Conf Artif Intell 32

  35. Rebuffi S-A, Kolesnikov A, Sperl G, Lampert CH (2017) iCaRL: incremental classifier and representation learning. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR). pp 5533–5542

  36. Kirkpatrick J, Pascanu R, Rabinowitz N et al (2017) Overcoming catastrophic forgetting in neural networks. Proc Natl Acad Sci USA 114:3521–3526. https://doi.org/10.1073/pnas.1611835114

    Article  MathSciNet  MATH  Google Scholar 

  37. Chaudhry A, Dokania PK, Ajanthan T, Torr PHS (2018) Riemannian walk for incremental learning: understanding forgetting and intransigence. Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics) 11215 LNCS. pp 556–572. https://doi.org/10.1007/978-3-030-01252-6_33

  38. Schwarz J, Czarnecki W, Luketina J, et al (2018) Progress and compress: a scalable framework for continual learning. In: Dy J, Krause A (eds) Proceedings of the 35th international conference on machine learning. PMLR, pp 4528–4537

  39. Aljundi R, Babiloni F, Elhoseiny M, et al (2018) Memory aware synapses: learning what (not) to forget. Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics) 11207 LNCS. pp 144–161. https://doi.org/10.1007/978-3-030-01219-9_9

  40. Li Z, Hoiem D (2018) Learning without forgetting. IEEE Trans Pattern Anal Mach Intell 40:2935–2947. https://doi.org/10.1109/TPAMI.2017.2773081

    Article  Google Scholar 

  41. Castro FM, Marín-Jiménez MJ, Guil N, et al (2018) end-to-end incremental learning. Lect notes comput sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics) 11216 LNCS. pp 241–257. https://doi.org/10.1007/978-3-030-01258-8_15

  42. Dhar P, Singh RV, Peng KC, et al (2019) Learning without memorizing. Proc IEEE comput soc conf comput vis pattern recognit 2019-June. pp 5133–5141. https://doi.org/10.1109/CVPR.2019.00528

  43. Sun J, Wang S, Zhang J, Zong C (2020) Distill and replay for continual language learning. In: Proceedings of the 28th international conference on computational linguistics. pp 3569–3579

  44. Monaikul N, Castellucci G, Filice S, Rokhlenko O (2021) Continual learning for named entity recognition. Proc AAAI Conf Artif Intell 35:13570–13577

    Google Scholar 

  45. Roy D, Panda P, Roy K (2020) Tree-CNN: a hierarchical deep convolutional neural network for incremental learning. Neural Netw 121:148–160. https://doi.org/10.1016/j.neunet.2019.09.010

    Article  Google Scholar 

  46. Yosinski J, Clune J, Bengio Y, Lipson H (2014) How transferable are features in deep neural networks? In: Ghahramani Z, Welling M, Cortes C et al (eds) Advances in neural information processing systems. Curran Associates Inc, New York

    Google Scholar 

  47. Wu C, Herranz L, Liu X et al (2018) Memory replay GANs: learning to generate images from new categories without forgetting. In: Proceedings of the 32nd international conference on neural information processing systems. Curran Associates Inc., Red Hook, NY, USA, pp 5966–5976

  48. Hayes TL, Kafle K, Shrestha R et al (2020) REMIND your neural network to prevent catastrophic forgetting. Lect Notes Comput Sci (including Subser Lect Notes Artif Intell Lect Notes Bioinformatics) 12353 LNCS. pp 466–483. https://doi.org/10.1007/978-3-030-58598-3_28

  49. Li Y, Zhang T (2017) Deep neural mapping support vector machines. Neural Netw 93:185–194. https://doi.org/10.1016/j.neunet.2017.05.010

    Article  MATH  Google Scholar 

  50. Xiao H, Rasul K, Vollgraf R (2017) Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. arXiv Prepr 1–6. http://arxiv.org/abs/1708.07747

  51. LeCun Y Cortes CORINNA BC MNIST handwritten digit database. http://yann.lecun.com/exdb/mnist/

  52. Clanuwat T, Bober-Irizar M, Kitamoto A, et al (2018) Deep learning for classical Japanese literature. arXiv Prepr 1–8. https://arxiv.org/abs/1812.01718

  53. Prabhu VU (2019) Kannada-MNIST: a new handwritten digits dataset for the Kannada language. arXiv Prepr 1–21. http://arxiv.org/abs/1908.01242

  54. Bulatov Y (2011) notMNIST dataset. https://yaroslavvb.blogspot.com/2011/09/notmnist-dataset.html

Download references

Acknowledgements

Our paper is supported by the National Natural Science Foundation of China (61806013, 61876010, 61906005), General project of Science and Technology Plan of Beijing Municipal Education Commission (KM202110005028), Project of Interdisciplinary Research Institute of Beijing University of Technology (2021020101) and International Research Cooperation Seed Fund of Beijing University of Technology (2021A01).

Author information

Authors and Affiliations

  1. Faculty of Information Technology, Beijing University of Technology, Beijing, 100124, China

    Jidong Han, Ting Zhang, Yujian Li & Zhaoying Liu

  2. School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin, 541004, China

    Yujian Li

Authors
  1. Jidong Han
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Ting Zhang
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Yujian Li
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Zhaoying Liu
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding authors

Correspondence to Jidong Han or Yujian Li.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Han, J., Zhang, T., Li, Y. et al. RD-NMSVM: neural mapping support vector machine based on parameter regularization and knowledge distillation. Int. J. Mach. Learn. & Cyber. 13, 2785–2798 (2022). https://doi.org/10.1007/s13042-022-01563-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13042-022-01563-1

Keywords