Learning by Design: Structuring and Documenting the Human Choices in Machine Learning Development
The influence of machine learning (ML) is quickly spreading, and a number of recent technological innovations have applied ML as a central technology. However, ML development still requires a substantial amount of human expertise to be successful. The deliberation and expert judgment applied during ML development cannot be revisited or scrutinized if not properly documented, and this hinders the further adoption of ML technologies--especially in safety critical situations. In this paper, we present a method consisting of eight design questions, that outline the deliberation and normative choices going into creating a ML model. Our method affords several benefits, such as supporting critical assessment through methodological transparency, aiding in model debugging, and anchoring model explanations by committing to a pre hoc expectation of the model's behavior. We believe that our method can help ML practitioners structure and justify their choices and assumptions when developing ML models, and that it can help bridge a gap between those inside and outside the ML field in understanding how and why ML models are designed and developed the way they are.
Code (0)
등록된 구현이 없습니다.
Tasks
BIG-bench Machine LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
High-quality data augmentation for code comment classification
Code comments serve a crucial role in software development for documenting functionality, clarifying design choices, and assisting with issue tracking. They capture developers' insights about the surrounding source code,…
Data AugmentationLessons from the trenches on evaluating machine-learning systems in materials science
Measurements are fundamental to knowledge creation in science, enabling consistent sharing of findings and serving as the foundation for scientific discovery. As machine learning systems increasingly transform scientific…
scientific discoverySearching for High-Value Molecules Using Reinforcement Learning and Transformers
Reinforcement learning (RL) over text representations can be effective for finding high-value policies that can search over graphs. However, RL requires careful structuring of the search space and algorithm design to be …
reinforcement-learningReinforcement LearningReinforcement Learning (RL)Structuring the Space of Sociotechnical Alignment
Sociotechnical alignment concerns the social desirability of AI behavior and is thus inherently normative, not merely technical. While NLP research increasingly addresses its technical aspects, it often leaves underspeci…
Rastro-DM: data mining with a trail
This paper proposes a methodology for documenting data mining (DM) projects, Rastro-DM (Trail Data Mining), with a focus not on the model that is generated, but on the processes behind its construction, in order to leave…