Abstract
The very exciting and promising approaches of deep learning are immensely successful in processing large real world data sets, such as image recognition, speech recognition, and language translation. However, much research discovered that it has biases that arise in the design, production, deployment, and use of AI/ML technologies. In this paper, we first explain mathematically the causes of biases and then propose a way to evaluate biases based on testing results of neurons and auto-encoders in deep learning. Our interpretation views each neuron or autoencoder as an approximation of similarity measurement, of which grey-box testing results can be used to measure biases and finding ways to reduce them. We argue that monitoring deep learning network structures and parameters is an effective way to catch the sources of biases in deep learning.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Whittaker, M., Crawford, K., Dobbe, R., Fried, G., Kaziunas, E., Mathur, V., West, S.M., Richardson, R., Schultz, J. and Schwartz, O.: AI now report 2018. AI Now Institute at New York University (2018)
Binns, R.: Fairness in machine learning: lessons from political philosophy. In: Conference on Fairness, Accountability and Transparency, pp. 149–159, January2018
https://www.partnershiponai.org/. Accessed January 2020
Friedler, S.A., Scheidegger, C., Venkatasubramanian, S., Choudhary, S., Hamilton, E.P., Roth, D.: A comparative study of fairness-enhancing interventions in machine learning. In: Proceedings of the Conference on Fairness, Accountability, and Transparency, pp. 329–338. ACM, January 2019
Corbett-Davies, S., Goel, S.: The measure and mismeasure of fairness: a critical review of fair machine learning. arXiv preprint [CS] arXiv:1808.00023, 31 July 2018
https://www.tensorflow.org/. Accessed January 2020
https://keras.io/. Accessed January 2020
https://pytorch.org/. Accessed January 2020
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings of the 25th International Conference on Neural Information Processing Systems, pp. 1097–1105, 03–06 December 2012, Lake Tahoe, Nevada (2012)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)
Feng, X., Zhang, Y., Glass, J.: Speech feature denoising and dereverberation via deep autoencoders for noisy reverberant speech recognition. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1759–1763, May 2014
Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach. Prentice Hall Press, Upper Saddle River (2009)
https://nlp.stanford.edu/pubs/clark2019what.pdf. Accessed January 2020
Lei, N., Su, K., Cui, L., Yau, S.-T., Gu, D.X.: A geometric view of optimal transportation and generative model. arXiv: 1710.05488. https://arxiv.org/abs/1710.05488. Accessed November 2019
https://www.youtube.com/watch?v=5-Kqb80h9rk. Accessed November 2019
https://arxiv.org/abs/1611.03530. Accessed November 2019
https://arxiv.org/pdf/1806.09777.pdf. Accessed November 2019
Li, J.J., Rossikova, Y., Morreal, P.: Natural language translator correctness prediction. J. Comput. Sci. Appl. Inf. Technol. 1(1), 2–11 (2016). ISSN Number 2474–9257
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436–444 (2015)
Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798–1828 (2013)
Bengio, Y., LeCun, Y.: Scaling learning algorithms towards AI. In: Bottou, L., Chapelle, O., DeCoste, D., Weston, J. (eds.) Large Scale Kernel Machines. MIT Press, Cambridge (2007)
Hedayat, A.S., Sloane, N.J.A., Stufken, J.: Orthogonal Arrays: Theory and Applications. Springer, Heidelberg (2012)
Pryzant, R., Richard, D.M., Dass, N., Kurohashi, S., Jurafsky, D., Yang, D.: Automatically neutralizing subjective bias in text. https://arxiv.org/abs/1911.09709. Accessed March 2020
Acknowledgments
We would like to thank Kean STEMPact program for supporting us to conduct this research in the summer of 2019 and Google’s subsequent support through a TensorFlow research grant.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Jenny Li, J., Silva, T., Franke, M., Hai, M., Morreale, P. (2021). Evaluating Deep Learning Biases Based on Grey-Box Testing Results. In: Arai, K., Kapoor, S., Bhatia, R. (eds) Intelligent Systems and Applications. IntelliSys 2020. Advances in Intelligent Systems and Computing, vol 1250. Springer, Cham. https://doi.org/10.1007/978-3-030-55180-3_48
Download citation
DOI: https://doi.org/10.1007/978-3-030-55180-3_48
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-55179-7
Online ISBN: 978-3-030-55180-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)