메뉴 건너뛰기




Volumn 4, Issue , 2017, Pages 2976-2987

Understanding black-box predictions via influence functions

Author keywords

[No Author keywords available]

Indexed keywords

FORECASTING; LEARNING SYSTEMS; METHOD OF MOMENTS; NEURAL NETWORKS;

EID: 85048455773     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper
Times cited : (815)

References (49)
  • 6
    • 84867112504 scopus 로고    scopus 로고
    • Support vector machines under adversarial label noise
    • Biggio, B., Nelson, B., and Laskov, P. Support vector machines under adversarial label noise. ACML, 20: 97-112, 2011.
    • (2011) ACML , vol.20 , pp. 97-112
    • Biggio, B.1    Nelson, B.2    Laskov, P.3
  • 9
    • 84972496372 scopus 로고
    • Influential observations, high leverage points, and outliers in linear regression
    • Chatterjee, S. and Hadi, A. S. Influential observations, high leverage points, and outliers in linear regression. Statistical Science, pp. 379-393, 1986.
    • (1986) Statistical Science , pp. 379-393
    • Chatterjee, S.1    Hadi, A.S.2
  • 11
    • 18244390064 scopus 로고    scopus 로고
    • On robustness properties of convex risk minimization methods for pattern recognition
    • Christmann, A. and Steinwart, I. On robustness properties of convex risk minimization methods for pattern recognition. Journal of Machine Learning Research (JMLR), 5(0): 1007-1034, 2004.
    • (2004) Journal of Machine Learning Research (JMLR) , vol.5 , pp. 1007-1034
    • Christmann, A.1    Steinwart, I.2
  • 12
    • 84952094529 scopus 로고
    • Detection of influential observation in linear regression
    • Cook, R. D. Detection of influential observation in linear regression. Technometrics, 19: 15-18, 1977.
    • (1977) Technometrics , vol.19 , pp. 15-18
    • Cook, R.D.1
  • 14
    • 4243118724 scopus 로고
    • Characterizations of an empirical influence function for detecting influential cases in regression
    • Cook, R. D. and Weisberg, S. Characterizations of an empirical influence function for detecting influential cases in regression. Technometrics, 22: 495-508, 1980.
    • (1980) Technometrics , vol.22 , pp. 495-508
    • Cook, R.D.1    Weisberg, S.2
  • 16
    • 84987644106 scopus 로고    scopus 로고
    • Algorithmic transparency via quantitative input influence: Theory and experiments with learning systems
    • Datta, A., Sen, S., and Zick, Y. Algorithmic transparency via quantitative input influence: Theory and experiments with learning systems. In Security and Privacy (SP), 2016 IEEE Symposium on, pp. 598-617, 2016.
    • (2016) Security and Privacy (SP), 2016 IEEE Symposium on , pp. 598-617
    • Datta, A.1    Sen, S.2    Zick, Y.3
  • 23
    • 0010018048 scopus 로고
    • Unpublished memorandum, Bell Telephone laboratories, Murray Hill, NJ
    • Jaeckel, L. A. The infinitesimal jackknife. Unpublished memorandum, Bell Telephone laboratories, Murray Hill, NJ, 1972.
    • (1972) The Infinitesimal Jackknife
    • Jaeckel, L.A.1
  • 27
    • 0032203257 scopus 로고    scopus 로고
    • Gradient-based learning applied to document recognition
    • IEEE
    • LeCun, Y, Bottou, L., Bengio, Y., and Haffner, P. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11): 2278-2324, 1998.
    • (1998) Proceedings of the , vol.86 , Issue.11 , pp. 2278-2324
    • LeCun, Y.1    Bottou, L.2    Bengio, Y.3    Haffner, P.4
  • 30
    • 33646887390 scopus 로고
    • On the limited memory BFGS method for large scale optimization
    • Liu, D. C. and Nocedal, J. On the limited memory BFGS method for large scale optimization. Mathematical Programming, 45(1): 503-528, 1989.
    • (1989) Mathematical Programming , vol.45 , Issue.1 , pp. 503-528
    • Liu, D.C.1    Nocedal, J.2
  • 31
    • 84919816683 scopus 로고    scopus 로고
    • Efficient approximation of cross-validation for kernel methods using Bouligand influence function
    • Liu, Y., Jiang, S., and Liao, S. Efficient approximation of cross-validation for kernel methods using Bouligand influence function. In International Conference on Machine Learning (ICML), pp. 324-332, 2014.
    • (2014) International Conference on Machine Learning (ICML) , pp. 324-332
    • Liu, Y.1    Jiang, S.2    Liao, S.3
  • 35
    • 84904809957 scopus 로고    scopus 로고
    • Spam filtering with naive Bayes - Which naive Bayes?
    • Metsis, V., Androutsopoulos, I., and Paliouras, G. Spam filtering with naive Bayes - which naive Bayes? In CEAS, volume 17, pp. 28-69, 2006.
    • (2006) CEAS , vol.17 , pp. 28-69
    • Metsis, V.1    Androutsopoulos, I.2    Paliouras, G.3
  • 37
    • 0000255539 scopus 로고
    • Fast exact multiplication by the hessian
    • Pearlmutter, B. A. Fast exact multiplication by the hessian. Neural Computation, 6(1): 147-160, 1994.
    • (1994) Neural Computation , vol.6 , Issue.1 , pp. 147-160
    • Pearlmutter, B.A.1
  • 46
    • 0025388464 scopus 로고
    • Assessing influence on predictions from generalized linear models
    • Thomas, W. and Cook, R. D. Assessing influence on predictions from generalized linear models. Technometrics, 32(1): 59-65, 1990.
    • (1990) Technometrics , vol.32 , Issue.1 , pp. 59-65
    • Thomas, W.1    Cook, R.D.2


* 이 정보는 Elsevier사의 SCOPUS DB에서 KISTI가 분석하여 추출한 것입니다.