人在环设计周期--一个将设计冲刺、敏捷过程和机器学习与人类集成的过程框架
Human-in-the-Loop Design Cycles -- A Process Framework that Integrates Design Sprints, Agile Processes, and Machine Learning with Humans
摘要：
对机器学习模型的后台性质的更透明的需求导致了最近机器学习中的人在环的兴起，即将人类集成到机器学习模型的训练和应用中的过程。目前的工作认为，这一过程的要求并不代表一个障碍，而是一个机会，以优化设计过程。因此，这项工作提出了一个新的过程框架，人在学习循环（HILL）设计周期-一个设计过程，集成了敏捷和设计思维过程的结构元素，并控制训练的机器学习模型的人在循环。HILL设计循环过程通过定量的心理测量工具来取代定性的用户测试，以获得设计感知。生成的用户反馈用于训练机器学习模型，并沿着四个设计维度（新颖性、能量、简单性、工具）指导后续设计周期。将四维用户反馈映射到用户故事和优先级，设计冲刺因此将用户反馈直接转化为实现过程。循环中的人是质量工程师，他仔细检查收集的用户反馈，以防止无效数据进入机器学习模型训练。
英文摘要：
Demands on more transparency of the backbox nature of machine learning models have led to the recent rise of human-in-the-loop in machine learning, i.e. processes that integrate humans in the training and application of machine learning models. The present work argues that this process requirement does not represent an obstacle but an opportunity to optimize the design process. Hence, this work proposes a new process framework, Human-in-the-learning-loop (HILL) Design Cycles - a design process that integrates the structural elements of agile and design thinking process, and controls the training of a machine learning model by the human in the loop. The HILL Design Cycles process replaces the qualitative user testing by a quantitative psychometric measurement instrument for design perception. The generated user feedback serves to train a machine learning model and to instruct the subsequent design cycle along four design dimensions (novelty, energy, simplicity, tool). Mapping the four-dimensional user feedback into user stories and priorities, the design sprint thus transforms the user feedback directly into the implementation process. The human in the loop is a quality engineer who scrutinizes the collected user feedback to prevents invalid data to enter machine learning model training.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
