nach oben

Erschienen in:

2024 | OriginalPaper | Buchkapitel

Learning Algorithm for Threshold Softmax Layer to Handle Unknown Class Problem

verfasst von : Gaurav Jaiswal

Erschienen in: Big Data, Machine Learning, and Applications

Verlag: Springer Nature Singapore

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config

KI-gestützte Suche

Aus

Abstract

Neural network are mostly trained with predefined class training data in supervised learning. But, when unknown test data (other than predefined class) are classified by a trained neural network, they are always misclassified into predefined classes, thus misclassification rate of trained neural network increases. To tackle these problems, Threshold Softmax Layer (TSM) and learning algorithm is proposed. In which, a normalized probability of each output class of the neural network is calculated and a threshold value is updated for each class during threshold learning process. If the maximum normalized probability of test data does not cross threshold value of the corresponding class, we will classify test data into unknown class. This TSM layer with neural network is evaluated on three UCI benchmark dataset (Glass, Yeast and Wine quality) and successfully handles the unknown class problem with reduced misclassification error.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

über 102.000 Bücher
über 537 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Finance + Banking
Management + Führung
Marketing + Vertrieb
Maschinenbau + Werkstoffe
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 390 Zeitschriften

aus folgenden Fachgebieten:

Automobil + Motoren
Bauwesen + Immobilien
Business IT + Informatik
Elektrotechnik + Elektronik
Energie + Nachhaltigkeit
Maschinenbau + Werkstoffe

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

über 67.000 Bücher
über 340 Zeitschriften

aus folgenden Fachgebieten:

Bauwesen + Immobilien
Business IT + Informatik
Finance + Banking
Management + Führung
Marketing + Vertrieb
Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Vorheriges Kapitel A Comparative Study of Loss Functions for Deep Neural Networks in Time Series Analysis

Nächstes Kapitel Traffic Monitoring and Violation Detection Using Deep Learning

Agatonovic-Kustrin S, Beresford R (2000) Basic concepts of artificial neural network (ann) modeling and its application in pharmaceutical research. J Pharm Biomed Anal 22(5):717–727CrossRef

Bendale A, Boult T (2015) Towards open world recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1893–1902

Bendale A, Boult TE (2016) Towards open set deep networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1563–1572

Costa FDO, Silva E, Eckmann M, Scheirer WJ, Rocha A (2014) Open set source camera attribution and device linking. Pattern Recognit Lett 39:92–101

Dheeru D, Karra Taniskidou E (2017) UCI machine learning repository. http://archive.ics.uci.edu/ml

Duch W, Jankowski N (1999) Survey of neural transfer functions. Neural Comput Surv 2(1):163–212

Egmont-Petersen M, de Ridder D, Handels H (2002) Image processing with neural networks-a review. Pattern Recognit 35(10):2279–2301CrossRefMATH

Ganis M, Wilson CL, Blue JL (1998) Neural network-based systems for handprint ocr applications. IEEE Trans Image Process 7(8):1097–1112CrossRef

Ge Z, Demyanov S, Chen Z, Garnavi R (2017) Generative openmax for multi-class open set classification. In: British machine vision conference 2017. British machine vision association and society for pattern recognition

10.

Geng C, Chen S (2018) Hierarchical dirichlet process-based open set recognition. arXiv:1806.11258

11.

Gorte B, Gorte-Kroupnova N (1995) Non-parametric classification algorithm with an unknown class. In: International symposium on computer vision, 1995. Proceedings. IEEE, pp 443–448

12.

Günther M, Cruz S, Rudd EM, Boult TE (2017) Toward open-set face recognition. In: Conference on computer vision and pattern recognition (CVPR) workshops. IEEE

13.

Gupta C, Wang S, Dayal U, Mehta A (2009) Classification with unknown classes. In: International conference on scientific and statistical database management. Springer, pp 479–496

14.

Hassen M, Chan PK (2020) Learning a neural-network-based representation for open set recognition. In: Proceedings of the 2020 SIAM international conference on data mining. SIAM, pp 154–162

15.

Jain LC, Halici U, Hayashi I, Lee S, Tsutsui S (1999) Intelligent biometric techniques in fingerprint and face recognition, vol 10. CRC Press

16.

Jain LP, Scheirer WJ, Boult TE (2014) Multi-class open set recognition using probability of inclusion. In: European conference on computer vision. Springer, pp 393–409

17.

Jaiswal G (2014) Handwritten devanagari character recognition model using neural network. Int J Eng Dev Res 901–906

18.

Jaiswal G (2021) Performance analysis of incremental learning strategy in image classification. In: 2021 11th international conference on cloud computing, data science and engineering (Confluence). IEEE, pp 427–432

19.

Jo I, Kim J, Kang H, Kim YD, Choi S (2018) Open set recognition by regularising classifier with fake data generated by generative adversarial networks. In: 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 2686–2690

20.

Júnior PRM, de Souza RM, Werneck RDO, Stein BV, Pazinato DV, de Almeida, WR, Penatti OA, Torres RDS, Rocha A (2017) Nearest neighbors distance ratio open-set classifier. Mach Learn 106(3):359–386

21.

Kannojia SP, Jaiswal G (2018) Ensemble of hybrid cnn-elm model for image classification. In: 2018 5th international conference on signal processing and integrated networks (SPIN). IEEE, pp 538–541

22.

Li F, Wechsler H (2005) Open set face recognition using transduction. IEEE Trans Pattern Anal Mach Intell 27(11):1686–1697CrossRef

23.

Lu CH, Tsai CC (2008) Adaptive predictive control with recurrent neural network for industrial processes: an application to temperature control of a variable-frequency oil-cooling machine. IEEE Trans Ind Electron 55(3):1366–1375CrossRef

24.

Miller A, Blott B et al (1992) Review of neural network applications in medical imaging and signal processing. Med Biol Eng Comput 30(5):449–464CrossRef

25.

Neira MAC, Júnior PRM, Rocha A, Torres RDS (2018) Data-fusion techniques for open-set recognition problems. IEEE Access 6:21242–21265CrossRef

26.

Paliwal M, Kumar UA (2009) Neural networks and statistical techniques: a review of applications. Expert Syst Appl 36(1):2–17CrossRef

27.

Raghupathi W, Schkade LL, Raju BS (1991) A neural network application for bankruptcy prediction. In: Proceedings of the twenty-fourth annual hawaii international conference on system sciences, vol 4. IEEE, pp 147–155

28.

Rattani A, Scheirer WJ, Ross A (2015) Open set fingerprint spoof detection across novel fabrication materials. IEEE Trans Inf Forensics Secur 10(11):2447–2460CrossRef

29.

Schalkoff RJ (1989) Digital image processing and computer vision, vol 286. Wiley, New York

30.

Scheirer WJ, Jain LP, Boult TE (2014) Probability models for open set recognition. IEEE Trans Pattern Anal Mach Intell 36(11):2317–2324CrossRef

31.

Scheirer WJ, de Rezende Rocha A, Sapkota A, Boult TE (2013) Toward open set recognition. IEEE Trans Pattern Anal Mach Intell 35(7):1757–1772CrossRef

32.

Shu L, Xu H, Liu B (2018) Unseen class discovery in open-world classification. arXiv:1801.05609

33.

Widrow B, Rumelhart DE, Lehr MA (1994) Neural networks: applications in industry, business and science. Commun ACM 37(3):93–106CrossRef

34.

Wong BK, Selvi Y (1998) Neural network applications in finance: a review and analysis of literature (1990–1996). Inf Manag 34(3):129–139CrossRef

35.

Xiao H, Sun J, Yu X, Wang L (2018) Compact binary feature for open set recognition. In: 2018 13th IAPR international workshop on document analysis systems (DAS). IEEE, pp 235–238

36.

Yu X, Sun J, Naoi S (2018) Generative adversarial networks for open set historical chinese character recognition. Electron Imaging 2018(2):1–5

37.

Zhang GP (2000) Neural networks for classification: a survey. IEEE Trans Syst, Man, Cybern, Part C (Applications and Reviews) 30(4):451–462

38.

Zhang H, Patel VM (2017) Sparse representation-based open set recognition. IEEE Trans Pattern Anal Mach Intell 39(8):1690–1696CrossRef

Titel: Learning Algorithm for Threshold Softmax Layer to Handle Unknown Class Problem
verfasst von: Gaurav Jaiswal
Verlag: Springer Nature Singapore
Buch: Big Data, Machine Learning, and Applications
Print ISBN: 978-981-9934-80-5

Electronic ISBN: 978-981-9934-81-2

Copyright-Jahr: 2024
DOI: https://doi.org/10.1007/978-981-99-3481-2_13

Springer Professional

Abstract

Bitte loggen Sie sich ein, um Zugang zu Ihrer Lizenz zu erhalten.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Springer Professional "Technik"

Springer Professional "Wirtschaft"

Premium Partner