Human and Machine Learning

Viac o knihe

With advancements in Machine Learning (ML) algorithms, data volumes, and computational power, ML has gained traction across various applications. However, the "black-box" nature of ML methods necessitates interpretation to ensure transparency and user acceptance of solutions. This edited volume addresses the connection between human and machine learning through the lenses of visualization, explanation, trustworthiness, and transparency. It explores transparency in ML, visual explanations of processes, algorithmic interpretations of models, human cognitive responses in ML decision-making, and the role of domain knowledge in transparent ML applications. This book is the first of its kind to systematically examine current research activities and outcomes related to human and machine learning. It aims to inspire researchers to develop new human-centered ML algorithms, fostering the overall advancement of the field. Additionally, it assists ML practitioners in leveraging outputs for informed and trustworthy decision-making. Targeted at researchers and practitioners in machine learning and its applications, the book is particularly beneficial for those in artificial intelligence, decision support systems, and human-computer interaction.