Training deep nets with imbalanced and unlabeled data

13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012

Volumn 2, Issue , 2012, Pages 1754-1757

  Berry, Jeff ^a,b   Fasel, Ian ^a   Fadiga, Luciano ^b,c   Archangeli, Diana ^a  

^a UNIVERSITY OF ARIZONA   (United States)

^b ISTITUTO ITALIANO DI TECNOLOGIA   (Italy)

^c UNIVERSITY OF FERRARA   (Italy)

Author keywords

Bootstrapping; Class imbalance problem; Deep belief networks; Speech processing; Tongue imaging; Ultrasound imaging

Indexed keywords

BOOTSTRAPPING; BOOTSTRAPPING METHOD; CLASS IMBALANCE PROBLEMS; DEEP BELIEF NETWORKS; DIVERSITY MEASURE; TWO-FOLD REDUCTION; ULTRASOUND IMAGES; ULTRASOUND IMAGING;

SPEECH PROCESSING; ULTRASONIC IMAGING;

ITERATIVE METHODS;

EID: 84878398857     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (15)

1. Hinton, G.E., and Osindero, S. & Teh, Y.W., "A fast learning algorithm for deep belief nets", Neur. Comp. 7(18): 1527-1554, 2006.
2. Salakhutdinov, R. & Hinton, G. "Learning a nonlinear embedding by preserving class neighbourhood structure", AI & Stat, 3(5), 2007.
3. Erhan, D., Bengio, Y., Courville, A., Manzagol, P.A., Vincent, P. and Bengio, S., "Why Does Unsupervised Pre-training Help Deep Learning?", J Mach Learn Res 11: 625-660, 2010.
4. Chawla, N.V., Japkowicz, N., & Kotcz, A., Editorial: special issue on learning from imbalanced data sets, ACM SIGKDD Explorations Newsletter 6(1): 1-6, 2004.
5. He, H. & Garcia, E.A., "Learning from imbalanced data", IEEE Trans Knowledge & Data Eng, 21(9), 1263-1284, 2009.
6. Cancho, R.F. & Sole, R.V., Least effort and the origins of scaling in human language, Proc. Nat Acad Sci 100: 788, 2003.
7. Zipf, G., Psycho-biology of languages, Houghton-Mifflin, 1935.
8. Liu, X.Y., Wu, J. & Zhou, Z.H., "Exploratory undersampling for class-imbalance learning", Systems, Man, and Cybernetics, B: Cyb, 39(2): 539-550, 2009.
9. Drummond, C. & Holte, R.C., "C4.5, class imbalance, and cost sensitivity: why under-sampling beats over-sampling", ICML, Workshop on Learning from Imbalanced Datasets, 2003.
10. Stone, M., "A guide to analysing tongue motion from ultrasound images", Clin ling & phon, 19(6-7): 455-501, 2005.
11. Iskarous, K., "Detecting the edge of the tongue: A tutorial", Clin ling & phon, 19(6-7): 555-565, 2005.
12. Gick, B., Campbell, F., Oh, S., & Tamburri-Watt, L., "Toward universals in the gestural organization of syllables: A cross-linguistic study of liquids", J Phon 34(1): 49-72, 2006.
13. Mielke, J., Baker, A. & Archangeli, D., Variability and Homogeneity in American English/ô/Allophony and/s/Retraction, Lab Phon 10, 699-730, Berlin: Mouton de Gruyter, 2011.
14. Li, M., Chandra, K. & Stone, M., "Automatic contour tracking in ultrasound images", Clin Ling & Phon, 19(6-7), 545-554, 2005.
15. Fasel, I. & Berry, J., "Deep belief networks for real-time extraction of tongue contours from ultrasound during speech", Int'l Conf Pat Rec, 2010.