| Title | Human-in-the-loop Approach towards Dual Process AI Decisions |
| Publication Type | Conference Paper |
| Year of Publication | 2020 |
| Authors | Uchida, Hikaru, Matsubara, Masaki, Wakabayashi, Kei, Morishima, Atsuyuki |
| Conference Name | 2020 IEEE International Conference on Big Data (Big Data) |
| Date Published | dec |
| Keywords | artificial intelligence, Big Data, crowd-sourcing, Dual-process Theory, explainable AI, human factors, human in the loop, image classification, Internet, Neural networks, psychology, pubcrawl, Training data |
| Abstract | How to develop AI systems that can explain how they made decisions is one of the important and hot topics today. Inspired by the dual-process theory in psychology, this paper proposes a human-in-the-loop approach to develop System-2 AI that makes an inference logically and outputs interpretable explanation. Our proposed method first asks crowd workers to raise understandable features of objects of multiple classes and collect training data from the Internet to generate classifiers for the features. Logical decision rules with the set of generated classifiers can explain why each object is of a particular class. In our preliminary experiment, we applied our method to an image classification of Asian national flags and examined the effectiveness and issues of our method. In our future studies, we plan to combine the System-2 AI with System-1 AI (e.g., neural networks) to efficiently output decisions. |
| DOI | 10.1109/BigData50022.2020.9378459 |
| Citation Key | uchida_human–-loop_2020 |
Human-in-the-loop Approach towards Dual Process AI Decisions