Understanding Potentially Biased Artificial Agents Powered by Supervised Learning: Perspectives from Cognitive Psychology and Cognitive Neuroscience

理解使用監督式學習而潛在有偏誤的人工代理者：認知心理學與認知神經科學的觀點

10.6129/CJP.201909_61(3).0002

黃從仁(Tsung-Ren Huang)

artificial intelligence ； cognitive neuroscience ； cognitive psychology ； deep learning ； machine learning ； 人工智慧 ； 深度學習 ； 認知心理學 ； 認知神經科學 ； 機器學習

中華心理學刊

61卷3期（2019 / 09 / 01）

197 - 208

英文

Despite being machines, many artificial agents, similar to humans, make biased decisions. The present article discusses when a machine learning system learns to make biased decisions and how to understand its potentially biased decision-making processes using methods developed or inspired by cognitive psychology and cognitive neuroscience. Specifically, we explain how the inductive nature of supervised machine learning leads to nontransparent decision biases, such as a relative ignorance of minority groups. By treating an artificial agent like a human research participant, we then review how to apply neural and behavioral methods from the cognitive sciences, such as brain ablation and image occlusion, to reveal the decision criteria and tendencies of an artificial agent. Finally, we discuss the social implications of biased artificial agents and encourage cognitive scientists to join the movement of uncovering and correcting machine biases.

人工代理者雖然是機器，但和人類一樣常會做出具有偏誤的決策。本文討論人工代理者中常用的機器學習系統何時會學習去做偏誤決策，以及如何使用認知心理學與認知神經科學中發展出來的方法來瞭解其具有偏誤的決策歷程。具體而言，我們會闡述本質上是歸納推理的監督式機器學習如何導致如忽略少數團體等不透明的決策偏誤。接著，我們會視一個人工代理者如一位人類研究參與者，回顧文獻中如何透過腦部切除與影像遮蔽等認知科學中的神經與行為方法來揭露一個人工代理者的決策準則與傾向。在文末，我們會討論有偏誤的人工代理者對於社會的影響，並鼓勵認知科學家們一同來揭示並改正機器的各種偏誤。

1. Angwin, J., Larson, J., Mattu, S., & Kirchner, L. (2016). Machine bias: There's software used across the country to predict future criminals and it's biased against blacks. ProPublica. Retrieved from https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing
2. Banich, M. T.,Compton, R. J.(2018).Cognitive Neuroscience.Cambridge University Press.
3. Bolukbasi, T.,Chang, K. W.,Zou, J. Y.,Saligrama, V.,Kalai, A. T.(2016).Man is to computer programmer as woman is to homemaker? Debiasing word embeddings.Advances in Neural Information Processing Systems
4. Buolamwini, J.,Gebru, T.(2018).Gender shades: Intersectional accuracy disparities in commercial gender classification.Conference on Fairness, Accountability and Transparency, PMLR 88
5. Caliskan, A.,Bryson, J. J.,Narayanan, A.(2017).Semantics derived automatically from language corpora contain human-like biases.Science,356(6334),183-186.
6. Cowan, N.(2008).What are the differences between long-term, short-term, and working memory?.Progress in Brain Research,169,323-338.
7. Duda, R. O.,Hart, P. E.,Stork, D. G.(2000).Pattern Classification.New York, NY:Wiley-Interscience.
8. Dwork, C.,Immorlica, N.,Kalai, A. T.,Leiserson, M. D.(2018).Decoupled classifiers for group-fair and efficient machine learning.Conference on Fairness, Accountability and Transparency, PMLR 81
9. Glauner, P.,Valtchev, P.,State, R.(2018).,未出版
10. Hardt, M.,Price, E.,Srebro, N.(2016).,未出版
11. Hassabis, D.,Kumaran, D.,Summerfield, C.,Botvinick, M.(2017).Neuroscience-inspired artificial intelligence.Neuron,95,245-258.
12. Johnson, K. O.,Hsiao, S. S.,Yoshioka, T.(2002).Neural coding and the basic law of psychophysics.The Neuroscientist,8,111-121.
13. Kahneman, D.(2002).Kahneman, D. (2002). Nobel Lecture. Stockholm, Sweden..
14. Karpathy, A.,Johnson, J.,Fei-Fei, L.(2015).,未出版
15. Kay, K. N.,Gallant, J. L.(2009).I can see what you see.Nature Neuroscience,12,245.
16. Kay, M.,Matuszek, C.,Munson, S. A.(2015).Unequal representation and gender stereotypes in image search results for occupations.Human Factors in Computing Systems
17. Kosinski, M.,Stillwell, D.,Graepel, T.(2013).Private traits and attributes are predictable from digital records of human behavior.Proceedings of the National Academy of Sciences,110,5802-5805.
18. Kosinski, M.,Wang, Y.(2018).Deep neural networks are more accurate than humans at detecting sexual orientation from facial images.Journal of Personality and Social Psychology,114,246-257.
19. Krawczyk, B.(2016).Learning from imbalanced data: open challenges and future directions.Progress in Artificial Intelligence,5,221-232.
20. Kriegeskorte, N.,Douglas, P. K.(2018).Cognitive computational neuroscience.Nature Neuroscience,21,1148-1160.
21. Lakkaraju, H.,Kamar, E.,Caruana, R.,Horvitz, E.(2016).,未出版
22. Leibo, J. Z.,d’Autume, C. D. M.,Zoran, D.,Amos, D.,Beattie, C.,Anderson, K.,Legg, S.(2018).,未出版
23. Mangun, G. R.(Ed.),Gazzaniga, M. S.(Ed.)(2014).The Cognitive Neurosciences.Cambridge, MA:MIT Press.
24. Metta, G.,Natale, L.,Nori, F.,Sandini, G.,Vernon, D.,Fadiga, L.,Bernardino, A.(2010).The iCub humanoid robot: An open-systems platform for research in cognitive development.Neural Networks,23,1125-1134.
25. Murray, R. F.(2011).Classification images: A review.Journal of Vision,11,2-2.
26. Naselaris, T.,Bassett, D. S.,Fletcher, A. K.,Kording, K.,Kriegeskorte, N.,Nienborg, H.,Kay, K.(2018).Cognitive computational neuroscience: A new conference for an emerging discipline.Trends in Conitive Sciences,22,365-367.
27. Rabinowitz, N. C.,Perbet, F.,Song, H. F.,Zhang, C.,Eslami, S. M.,Botvinick, M.(2018).,未出版
28. Reyna, V. F.,Chick, C. F.,Corbin, J. C.,Hsia, A. N.(2014).Developmental reversals in risky decision making: Intelligence agents show larger decision biases than college students.Psychological Science,25,76-84.
29. Rhodes, G.,Proffitt, F.,Grady, J. M.,Sumich, A.(1998).Facial symmetry and the perception of beauty.Psychonomic Bulletin & Review,5,659-669.
30. Ritter, S.,Barrett, D. G.,Santoro, A.,Botvinick, M. M.(2017).,未出版
31. Shanks, D. R.,Tunney, R. J.,McCarthy, J. D.(2002).A re-examination of probability matching and rational choice.Journal of Behavioral Decision Making,15,233-250.
32. Shen, G.,Dwivedi, K.,Majima, K.,Horikawa, T.,Kamitani, Y.(2018).,未出版
33. Silver, D.,Schrittwieser, J.,Simonyan, K.,Antonoglou, I.,Huang, A.,Guez, A.,Chen, Y.(2017).Mastering the game of Go without human knowledge.Nature,550(7676),354-359.
34. Sloman, S. A.,Lagnado, D.(2005).The Cambridge handbook of thinking and reasoning.
35. Wilson, R. A.(Ed.),Keil, F. C.(Ed.)(1999).The MIT encyclopedia of the cognitive sciences.Cambridge, MA:MIT press.
36. Wu, X.,Zhang, X.(2016).,未出版
37. Wykowska, A.,Chaminade, T.,Cheng, G.(2016).Embodied artificial agents for understanding human social cognition.Philosophical Transactions of the Royal Society B: Biological Sciences,371,20150375.
38. Xie, D.,Liang, L.,Jin, L.,Xu, J.,Li, M.(2015).,未出版
39. Yarkoni, T.,Westfall, J.(2017).Choosing prediction over explanation in psychology: Lessons from machine learning.Perspectives on Psychological Science,12,1100-1122.
40. Youyou, W.,Kosinski, M.,Stillwell, D.(2015).Computer-based personality judgments are more accurate than those made by humans.Proceedings of the National Academy of Sciences,112,1036-1040.
41. Zeiler, M. D.,Fergus, R.(2014).Visualizing and understanding convolutional networks.European Conference on Computer Vision,Cham, Switzerland:
42. Zhao, J.,Wang, T.,Yatskar, M.,Ordonez, V.,Chang, K. W.(2017).,未出版

1. 黃碧群,陳建中(2020)。人臉美感知覺：影像統計數和對稱感的影響。中華心理學刊，62(3)，421-440。
2. 黃從仁(2020)。大數據與人工智慧方法在行為與社會科學的應用趨勢。調查研究-方法與應用，45，11-42。