Convolutional neural support vector machines: Hybrid visual pattern classifiers for multi-robot systems

Proceedings - 2012 11th International Conference on Machine Learning and Applications, ICMLA 2012

Volumn 1, Issue , 2012, Pages 27-32

  Nagi, Jawad ^a   Caro, Gianni A Di ^a   Giusti, Alessandro ^a   Nagi, Farrukh ^b   Gambardella, Luca M ^a  

^a DALLE MOLLE INSTITUTE FOR ARTIFICIAL INTELLIGENCE IDSIA   (Switzerland)

^b Universiti Tenaga Nasional   (Malaysia)

Author keywords

Convolutional Neural Networks; Multi robot Systems; Supervised Learning; Support Vector Machines; Swarm Robotics

Indexed keywords

COMPUTATIONAL CAPABILITY; CONVOLUTIONAL NEURAL NETWORK; HAND GESTURE; LEARNING PROGRESS; LEARNING SCENARIOS; MULTI-ROBOT SYSTEMS; ONLINE INCREMENTAL LEARNING; STOCHASTIC GRADIENT DESCENT; SUPERVISED CLASSIFICATION; SUPPORT VECTOR MACHINE (SVMS); SWARM ROBOTICS; TRAINING SAMPLE; VISUAL LEARNING; VISUAL PATTERN;

CONVOLUTION; MULTIPURPOSE ROBOTS; NEURAL NETWORKS; ROBOT LEARNING; SUPERVISED LEARNING;

SUPPORT VECTOR MACHINES;

EID: 84873606887     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICMLA.2012.14     Document Type: Conference Paper

References (25)

1. A. Giusti, J. Nagi, L. Gambardella, and G. A. DiCaro, "Cooperative sensing and recognition by a swarmof mobile robots," in Proc. of the 25th IEEE/RSJInternational Conference on Intelligent Robots andSystems (IROS), 2012, pp. 551-558.
2. J. Nagi, H. Ngo, A. Giusti, L. M. Gambardella,J. Schmidhuber, and G. A. Di Caro, "Incremental learningusing partial feedback for gesture-based humanswarminteraction," in Proc. of the 21st IEEE InternationalSymposium on Robot and Human InteractiveCommunication (RO-MAN), 2012, pp. 898-905.
3. J. Nagi, F. Ducatelle, G. A. Di Caro, D. Ciresan,U. Meier, A. Giusti, F. Nagi, et al., "Max-poolingconvolutional neural networks for vision-based handgesture recognition," in Proc. of the 2nd IEEE InternationalConference on Signal and Image ProcessingApplications (ICSIPA), 2011, pp. 342-347.
4. T.-N. Do and J.-D. Fekete, "Large scale classificationwith support vector machine algorithms," in Proc. ofthe 6th ICMLA, 2007, pp. 7-12.
5. Y. LeCun, L. Bottou, Y. Bengio, et al., "Gradient-basedlearning applied to document recognition," Proc. of theIEEE, vol. 86, no. 11, pp. 2278-2324, Nov. 1998.
6. K. Boukharouba, L. Bako, et al., "Incremental anddecremental multi-category classification by supportvector machines," in Proc. of 8th ICMLA, 2009, pp.294-300.
7. A. Bellili et al., "An hybrid mlp-svm handwritten digitrecognizer," in Proc. of the Intl. Conf. on DocumentAnalysis and Recognition (ICDAR), 2001, pp. 28-32.
8. W. W. Azevedo and C. Zanchettin, "A MLP-SVMhybrid model for cursive handwriting recognition," inProc. of the IJCNN, 2011, pp. 843-850.
9. F. Lauer, C. Y. Suen, and G. Bloch, "A trainable featureextractor for handwritten digit recognition," PatternRecognition, vol. 40, no. 6, pp. 1816-1824, 2007.
10. X.-X. Niu and C. Y. Ching, "A novel hybrid cnn-svmclassifier for recognizing handwritten digits," PatternRecognition, vol. 45, no. 4, pp. 1318-1325, Apr. 2012.
11. A. Borji, "Combining heterogeneous classifiers fornetwork intrusion detection," in Proc. of the 12th AsianComputing Science Conf. (ASIAN), 2007, pp. 254-260.
12. K. Mori, M. Matsugu, and T. Suzuki, "Face recognitionusing svm fed with intermediate output of cnn for facedetection," in Proc. of the IAPR Conf. on MachineVision Applications (MVA), 2005, pp. 410-413.
13. H. Long andW. K. Leow, "A hybrid model for invariantand perceptual texture mapping," in Proc. of the Intl.Conf. on Pattern Recog. (ICPR), 2002, pp. 135-138.
14. M. Szarvas et al., "Pedestrian detection with convolutionalneural networks," in Proc. of the IEEE Symp. onIntell. Vehicles (IV), 2005, pp. 224-229.
15. F.-J. Huang et al., "Large-scale learning with svm andconvolutional nets for generic object categorization," inProc. of the IEEE Intl. Conf. on CVPR, 2006.
16. D. Cireşan, U. Meier, J. Masci, L. M. Gambardella,and J. Schmidhuber, "Flexible, high performance convolutionalneural networks for image classification," inProc. of 22nd IJCAI, 2011, pp. 1237-1242.
17. J. A. K. Suykens and J. Vandewalle, "Training multilayerperceptron classifiers based on a modified supportvector method," IEEE Transactions on Neural Networks,vol. 10, no. 4, pp. 907-911, Jul. 1999.
18. S. Abdelazeem, "A greedy approach for building classificationcascades," in Proc. of the 7th ICMLA, 2008,pp. 115-120.
19. P. Ghanty, S. Paul, and N. R. Pal, "NEUROSVM: Anarchitecture to reduce the effect of the choice of kernelon the performance of svm," J. of Machine LearningResearch, vol. 10, pp. 591-622, Jun. 2009.
20. L. Zhang, W. Zhou, and L. Jiao, "Hidden space supportvector machines," IEEE Transactions on NeuralNetworks, vol. 15, no. 6, pp. 1424-1434, Nov. 2004.
21. R. Collobert and S. Bengio, "Links between perceptrons,mlps and svms," in Proc. of the 21st ICML, 2004.
22. R. Wijnhoven and P. de With, "Fast training of objectdetection using stochastic gradient descent," in Proc.of the ICPR, Aug. 2010, pp. 424-427.
23. D. H. Wiesel et al., "Receptive fields, binocular interactionand functional architecture in the cat's visualcortex," J. of Physio., vol. 160, pp. 106-154, Jan. 1962.
24. V. Vapnik, The nature of statistical learning theory.New York, NY, USA: Springer-Verlag, 1995.
25. T. Zhang, "Solving large scale linear prediction problemsusing stochastic gradient descent algorithms," inProc. of the 21st ICML, 2004.