Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence Using Multiple Models to Understand Data

Citations in the corpus

• Rewriting a Deep Generative Model (2020, neutral): “and hyperparameter selection [39,61,37].”
• Interacting with Predictions: Visual Inspection of Black-box Machine Learning Models (2016, methodology): “[33] use multiple classifiers to better understand input data.”
• Explaining Decision-Making Algorithms through UI: Strategies to Help Non-Expert Stakeholders (2019, background): “First, the majority of these techniques and tools are designed to support expert users like data scientists and ML practitioners (e.g. [2, 29, 31, 41, 44]) or serve educational purposes for people who are machine learning novices but often have good technical literacy [46].”
• FeatureInsight: Visual support for error-driven feature ideation in text classification (2015, methodology): “Patel et al. proposed comparing example data from a classifier's " confused region " with a representative example from the opposite class to help users think of new discriminating features [17].”
• Interactive Machine Learning via a GPU-accelerated Toolkit (2017, unknown): “The Prospect system [30] automates model selection and tuning allowing users to focus on data manipulation.”
• ModelTracker: Redesigning Performance Analysis Tools for Machine Learning (2015, methodology): “[17] used a scatterplot to visualize the results of multiple models simultaneously during the machine learning process.”
• Trends and Trajectories for Explainable, Accountable and Intelligible Systems: An HCI Research Agenda (2018, background): “We already see some examples of research in this direction, such as studies on understanding how data scientists work [97], tools to support data scientists in using and understanding machine-learning algorithms [99, 130, 142, 141],”