Author name cluster

Nicholas Gisolfi

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

1 author row

AAAI Conference 2024 Short Paper

Data-Driven Discovery of Design Specifications (Student Abstract)

Angela Chen
Nicholas Gisolfi
Artur Dubrawski

Ensuring a machine learning model’s trustworthiness is crucial to prevent potential harm. One way to foster trust is through the formal verification of the model’s adherence to essential design requirements. However, this approach relies on well-defined, application-domain-centric criteria with which to test the model, and such specifications may be cumbersome to collect in practice. We propose a data-driven approach for creating specifications to evaluate a trained model effectively. Implementing this framework allows us to prove that the model will exhibit safe behavior while minimizing the false-positive prediction rate. This strategy enhances predictive accuracy and safety, providing deeper insight into the model’s strengths and weaknesses, and promotes trust through a systematic approach.

PDF Details DOI

AAAI Conference 2023 Short Paper

Ordinal Programmatic Weak Supervision and Crowdsourcing for Estimating Cognitive States (Student Abstract)

Prakruthi Pradeep
Benedikt Boecking
Nicholas Gisolfi
Jacob R. Kintz
Torin K. Clark
Artur Dubrawski

Crowdsourcing and weak supervision offer methods to efficiently label large datasets. Our work builds on existing weak supervision models to accommodate ordinal target classes, in an effort to recover ground truth from weak, external labels. We define a parameterized factor function and show that our approach improves over other baselines.

PDF Details DOI

AAAI Conference 2022 Short Paper

Actionable Model-Centric Explanations (Student Abstract)

Cecilia G. Morales
Nicholas Gisolfi
Robert Edman
James K. Milller
Artur Dubrawski

We recommend using a model-centric, Boolean Satisfiability (SAT) formalism to obtain useful explanations of trained model behavior, different and complementary to what can be gleaned from LIME and SHAP, popular data-centric explanation tools in Artificial Intelligence (AI). We compare and contrast these methods, and show that data-centric methods may yield brittle explanations of limited practical utility. The model-centric framework, however, can offer actionable insights into risks of using AI models in practice. For critical applications of AI, split-second decision making is best informed by robust explanations that are invariant to properties of data, the capability offered by model-centric frameworks.

PDF Details