[HTML][HTML] Evaluating the quality of machine learning explanations: A survey on methods and metrics
The most successful Machine Learning (ML) systems remain complex black boxes to end-
users, and even experts are often unable to understand the rationale behind their decisions …
users, and even experts are often unable to understand the rationale behind their decisions …
[HTML][HTML] Deep learning in the construction industry: A review of present status and future innovations
The construction industry is known to be overwhelmed with resource planning, risk
management and logistic challenges which often result in design defects, project delivery …
management and logistic challenges which often result in design defects, project delivery …
Explainable deep learning: A field guide for the uninitiated
Deep neural networks (DNNs) are an indispensable machine learning tool despite the
difficulty of diagnosing what aspects of a model's input drive its decisions. In countless real …
difficulty of diagnosing what aspects of a model's input drive its decisions. In countless real …
The what-if tool: Interactive probing of machine learning models
A key challenge in developing and deploying Machine Learning (ML) systems is
understanding their performance across a wide range of inputs. To address this challenge …
understanding their performance across a wide range of inputs. To address this challenge …
Software engineering for machine learning: A case study
Recent advances in machine learning have stimulated widespread interest within the
Information Technology sector on integrating AI capabilities into software and services. This …
Information Technology sector on integrating AI capabilities into software and services. This …
Improving fairness in machine learning systems: What do industry practitioners need?
The potential for machine learning (ML) systems to amplify social inequities and unfairness
is receiving increasing popular and academic attention. A surge of recent work has focused …
is receiving increasing popular and academic attention. A surge of recent work has focused …
Toward trustworthy AI development: mechanisms for supporting verifiable claims
With the recent wave of progress in artificial intelligence (AI) has come a growing awareness
of the large-scale impacts of AI systems, and recognition that existing regulations and norms …
of the large-scale impacts of AI systems, and recognition that existing regulations and norms …
Understanding black-box predictions via influence functions
How can we explain the predictions of a black-box model? In this paper, we use influence
functions—a classic technique from robust statistics—to trace a model's prediction through …
functions—a classic technique from robust statistics—to trace a model's prediction through …
[HTML][HTML] The building blocks of interpretability
With the growing success of neural networks, there is a corresponding need to be able to
explain their decisions—including building confidence about how they will behave in the …
explain their decisions—including building confidence about how they will behave in the …
Collaboration challenges in building ml-enabled systems: Communication, documentation, engineering, and process
The introduction of machine learning (ML) components in software projects has created the
need for software engineers to collaborate with data scientists and other specialists. While …
need for software engineers to collaborate with data scientists and other specialists. While …