As machine learning models are playing increasingly important roles in many real-life scenarios, interpretability has become a key issue for whether we can trust the predictions made by these models, especially when we are making some high-stakes decisions. Lack of transparency has long been a concern for predictive models in criminal justice and in healthcare. There have been growing calls for building interpretable, human understandable machine learning models, and \"opening the black box\" has become a debated issue in the media. My dissertation research addresses precisely the demand for interpretability and transparency in machine learning models. The key problem of this dissertation is: \"Can we build machine learning models that are both accurate and interpretable?\"
To address this problem, I will discuss the notion of interpretability as it relates to machine learning, and present several new interpretable machine learning models and methods I developed during my dissertation research. In Chapter 1, I will discuss two types of model interpretability -- predicate-based and case-based interpretability. In Chapters 2 and 3, I will present novel predicate-based interpretable models and methods, and their applications to understanding low-dimensional structured data. In particular, Chapter 2 presents falling rule lists, which extend regular decision lists by requiring the probabilities of the desired outcome to be monotonically decreasing down the list; Chapter 3 presents two-layer additive models, which are hybrids of predicate-based additive scoring models and small neural networks. In Chapter 4, I will present case-based interpretable deep models, and their applications to computer vision. Given the empirical evidence, I conclude in Chapter 5 that, by designing novel model architectures or regularization techniques, we can build machine learning models that are both accurate and interpretable.
","abstract_html":"<p>As machine learning models are playing increasingly important roles in many real-life scenarios, interpretability has become a key issue for whether we can trust the predictions made by these models, especially when we are making some high-stakes decisions. Lack of transparency has long been a concern for predictive models in criminal justice and in healthcare. There have been growing calls for building interpretable, human understandable machine learning models, and "opening the black box" has become a debated issue in the media. My dissertation research addresses precisely the demand for interpretability and transparency in machine learning models. The key problem of this dissertation is: "Can we build machine learning models that are both accurate and interpretable?"</p><p>To address this problem, I will discuss the notion of interpretability as it relates to machine learning, and present several new interpretable machine learning models and methods I developed during my dissertation research. In Chapter 1, I will discuss two types of model interpretability -- predicate-based and case-based interpretability. In Chapters 2 and 3, I will present novel predicate-based interpretable models and methods, and their applications to understanding low-dimensional structured data. In particular, Chapter 2 presents falling rule lists, which extend regular decision lists by requiring the probabilities of the desired outcome to be monotonically decreasing down the list; Chapter 3 presents two-layer additive models, which are hybrids of predicate-based additive scoring models and small neural networks. In Chapter 4, I will present case-based interpretable deep models, and their applications to computer vision. Given the empirical evidence, I conclude in Chapter 5 that, by designing novel model architectures or regularization techniques, we can build machine learning models that are both accurate and interpretable.</p>","abstract_has_math":false,"creators":["Chen, Chaofan"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Rudin, Cynthia"],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020","date_published":"2020","updated_at":"2026-07-24T02:07:19Z","subjects":["Computer science","Interpretability","Machine learning","Transparency"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10161/21036","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Rudin, Cynthia"]},{"key":"dc:creator","label":"Author","values":["Chen, Chaofan"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2020-06-10T15:19:11Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2020-06-10T15:19:11Z"]},{"key":"dc:date.issued","label":"Date","values":["2020"]},{"key":"dc:type","label":"Dc Type","values":["Dissertation"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Computer science","Interpretability","Machine learning","Transparency"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10161/21036"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["As machine learning models are playing increasingly important roles in many real-life scenarios, interpretability has become a key issue for whether we can trust the predictions made by these models, especially when we are making some high-stakes decisions. Lack of transparency has long been a concern for predictive models in criminal justice and in healthcare. There have been growing calls for building interpretable, human understandable machine learning models, and \"opening the black box\" has become a debated issue in the media. My dissertation research addresses precisely the demand for interpretability and transparency in machine learning models. The key problem of this dissertation is: \"Can we build machine learning models that are both accurate and interpretable?\"
To address this problem, I will discuss the notion of interpretability as it relates to machine learning, and present several new interpretable machine learning models and methods I developed during my dissertation research. In Chapter 1, I will discuss two types of model interpretability -- predicate-based and case-based interpretability. In Chapters 2 and 3, I will present novel predicate-based interpretable models and methods, and their applications to understanding low-dimensional structured data. In particular, Chapter 2 presents falling rule lists, which extend regular decision lists by requiring the probabilities of the desired outcome to be monotonically decreasing down the list; Chapter 3 presents two-layer additive models, which are hybrids of predicate-based additive scoring models and small neural networks. In Chapter 4, I will present case-based interpretable deep models, and their applications to computer vision. Given the empirical evidence, I conclude in Chapter 5 that, by designing novel model architectures or regularization techniques, we can build machine learning models that are both accurate and interpretable.
"]},{"key":"dc:title","label":"Title","values":["Interpretability by Design: New Interpretable Machine Learning Models and Methods"]}]}],"canonical_facts":{"dc:contributor.advisor":["Rudin, Cynthia"],"dc:creator":["Chen, Chaofan"],"dc:date.accessioned":["2020-06-10T15:19:11Z"],"dc:date.available":["2020-06-10T15:19:11Z"],"dc:date.issued":["2020"],"dc:description.abstract":["As machine learning models are playing increasingly important roles in many real-life scenarios, interpretability has become a key issue for whether we can trust the predictions made by these models, especially when we are making some high-stakes decisions. Lack of transparency has long been a concern for predictive models in criminal justice and in healthcare. There have been growing calls for building interpretable, human understandable machine learning models, and \"opening the black box\" has become a debated issue in the media. My dissertation research addresses precisely the demand for interpretability and transparency in machine learning models. The key problem of this dissertation is: \"Can we build machine learning models that are both accurate and interpretable?\"
To address this problem, I will discuss the notion of interpretability as it relates to machine learning, and present several new interpretable machine learning models and methods I developed during my dissertation research. In Chapter 1, I will discuss two types of model interpretability -- predicate-based and case-based interpretability. In Chapters 2 and 3, I will present novel predicate-based interpretable models and methods, and their applications to understanding low-dimensional structured data. In particular, Chapter 2 presents falling rule lists, which extend regular decision lists by requiring the probabilities of the desired outcome to be monotonically decreasing down the list; Chapter 3 presents two-layer additive models, which are hybrids of predicate-based additive scoring models and small neural networks. In Chapter 4, I will present case-based interpretable deep models, and their applications to computer vision. Given the empirical evidence, I conclude in Chapter 5 that, by designing novel model architectures or regularization techniques, we can build machine learning models that are both accurate and interpretable.
"],"dc:identifier.uri":["https://hdl.handle.net/10161/21036"],"dc:subject":["Computer science","Interpretability","Machine learning","Transparency"],"dc:title":["Interpretability by Design: New Interpretable Machine Learning Models and Methods"],"dc:type":["Dissertation"]},"updated_at":"2026-07-24T02:07:19Z"}