David W. Aha
Research Subjects
David W. Aha has a total of 65 co-authors. Here are the top co-authors by number of shared publications:
- Luke K. McDowell
U.S. Naval Academy
3 shared publications - Michael W. Floyd
Knexus Research Corporation
3 shared publications - Bartosz Krawczyk
Rochester Institute of Technology
2 shared publications - Colin Bellinger
National Research Council of Canada
2 shared publications - Damien Dablain
University of Notre Dame
2 shared publications - Mark A. Wilson
Navy Center for Applied Research in AI (Code 5510), Naval Research Laboratory, Washington, DC, USA. s:
2 shared publications
Latest Publications
- Open Access
- 16 January 2024
- Published by Springer Nature in Machine Learning
- Vol. 113 (6) , 3751-3769
Understanding imbalanced data: XAI & interpretable ML framework
There is a gap between current methods that explain deep learning models that work on imbalanced image data and the needs of the imbalanced learning community. Existing methods that explain imbalanced data are geared toward binary classification, single layer machine learning models and low dimensional data. Current eXplainable Artificial Intelligence (XAI) techniques for vision data mainly focus on mapping predictions of specific instances to inputs, instead of examining global data properties and complexities of entire classes. Therefore, there is a need for a framework that is tailored to modern deep networks, that incorporates large, high dimensional, multi-class datasets, and uncovers data complexities commonly found in imbalanced data. We propose a set of techniques that can be used by both deep learning model users to identify, visualize and understand class prototypes, sub-concepts and outlier instances; and by imbalanced learning algorithm developers to detect features and class exemplars that are key to model performance. The components of our framework can be applied sequentially in their entirety or individually, making it fully flexible to the user’s specific needs (https://github.com/dd1github/XAI_for_Imbalanced_Learning).
- 16 January 2024
- Published by Springer Nature in Machine Learning
- Vol. 113 (6) , 3751-3769
Open AccessUnderstanding imbalanced data: XAI & interpretable ML framework
There is a gap between current methods that explain deep learning models that work on imbalanced image data and the needs of the imbalanced learning community. Existing methods that explain imbalanced data are geared toward binary classification, single layer machine learning models and low dimensional data. Current eXplainable Artificial Intelligence (XAI) techniques for vision data mainly focus on mapping predictions of specific instances to inputs, instead of examining global data properties and complexities of entire classes. Therefore, there is a need for a framework that is tailored to modern deep networks, that incorporates large, high dimensional, multi-class datasets, and uncovers data complexities commonly found in imbalanced data. We propose a set of techniques that can be used by both deep learning model users to identify, visualize and understand class prototypes, sub-concepts and outlier instances; and by imbalanced learning algorithm developers to detect features and class exemplars that are key to model performance. The components of our framework can be applied sequentially in their entirety or individually, making it fully flexible to the user’s specific needs (https://github.com/dd1github/XAI_for_Imbalanced_Learning).
- Open Access
Interpretable ML for Imbalanced Data
Deep learning models are being increasingly applied to imbalanced data in high stakes fields such as medicine, autonomous driving, and intelligence analysis. Imbalanced data compounds the black-box nature of deep networks because the relationships between classes may be highly skewed and unclear. This can reduce trust by model users and hamper the progress of developers of imbalanced learning algorithms. Existing methods that investigate imbalanced data complexity are geared toward binary classification, shallow learning models and low dimensional data. In addition, current eXplainable Artificial Intelligence (XAI) techniques mainly focus on converting opaque deep learning models into simpler models (e.g., decision trees) or mapping predictions for specific instances to inputs, instead of examining global data properties and complexities. Therefore, there is a need for a framework that is tailored to modern deep networks, that incorporates large, high dimensional, multi-class datasets, and uncovers data complexities commonly found in imbalanced data (e.g., class overlap, sub-concepts, and outlier instances). We propose a set of techniques that can be used by both deep learning model users to identify, visualize and understand class prototypes, sub-concepts and outlier instances; and by imbalanced learning algorithm developers to detect features and class exemplars that are key to model performance. Our framework also identifies instances that reside on the border of class decision boundaries, which can carry highly discriminative information. Unlike many existing XAI techniques which map model decisions to gray-scale pixel locations, we use saliency through back-propagation to identify and aggregate image color bands across entire classes. Our framework is publicly available at \url{https://github.com/dd1github/XAI_for_Imbalanced_Learning}
Open AccessInterpretable ML for Imbalanced Data
Deep learning models are being increasingly applied to imbalanced data in high stakes fields such as medicine, autonomous driving, and intelligence analysis. Imbalanced data compounds the black-box nature of deep networks because the relationships between classes may be highly skewed and unclear. This can reduce trust by model users and hamper the progress of developers of imbalanced learning algorithms. Existing methods that investigate imbalanced data complexity are geared toward binary classification, shallow learning models and low dimensional data. In addition, current eXplainable Artificial Intelligence (XAI) techniques mainly focus on converting opaque deep learning models into simpler models (e.g., decision trees) or mapping predictions for specific instances to inputs, instead of examining global data properties and complexities. Therefore, there is a need for a framework that is tailored to modern deep networks, that incorporates large, high dimensional, multi-class datasets, and uncovers data complexities commonly found in imbalanced data (e.g., class overlap, sub-concepts, and outlier instances). We propose a set of techniques that can be used by both deep learning model users to identify, visualize and understand class prototypes, sub-concepts and outlier instances; and by imbalanced learning algorithm developers to detect features and class exemplars that are key to model performance. Our framework also identifies instances that reside on the border of class decision boundaries, which can carry highly discriminative information. Unlike many existing XAI techniques which map model decisions to gray-scale pixel locations, we use saliency through back-propagation to identify and aggregate image color bands across entire classes. Our framework is publicly available at \url{https://github.com/dd1github/XAI_for_Imbalanced_Learning}
- Open Access
Dungeon Crawl Stone Soup as an Evaluation Domain for Artificial Intelligence
Dungeon Crawl Stone Soup is a popular, single-player, free and open-source rogue-like video game with a sufficiently complex decision space that makes it an ideal testbed for research in cognitive systems and, more generally, artificial intelligence. This paper describes the properties of Dungeon Crawl Stone Soup that are conducive to evaluating new approaches of AI systems. We also highlight an ongoing effort to build an API for AI researchers in the spirit of recent game APIs such as MALMO, ELF, and the Starcraft II API. Dungeon Crawl Stone Soup's complexity offers significant opportunities for evaluating AI and cognitive systems, including human user studies. In this paper we provide (1) a description of the state space of Dungeon Crawl Stone Soup, (2) a description of the components for our API, and (3) the potential benefits of evaluating AI agents in the Dungeon Crawl Stone Soup video game.
Open AccessDungeon Crawl Stone Soup as an Evaluation Domain for Artificial Intelligence
Dungeon Crawl Stone Soup is a popular, single-player, free and open-source rogue-like video game with a sufficiently complex decision space that makes it an ideal testbed for research in cognitive systems and, more generally, artificial intelligence. This paper describes the properties of Dungeon Crawl Stone Soup that are conducive to evaluating new approaches of AI systems. We also highlight an ongoing effort to build an API for AI researchers in the spirit of recent game APIs such as MALMO, ELF, and the Starcraft II API. Dungeon Crawl Stone Soup's complexity offers significant opportunities for evaluating AI and cognitive systems, including human user studies. In this paper we provide (1) a description of the state space of Dungeon Crawl Stone Soup, (2) a description of the components for our API, and (3) the potential benefits of evaluating AI agents in the Dungeon Crawl Stone Soup video game.
- 2 March 2018
- Published by SAGE Publications in AI Communications
- Vol. 31 (2) , 213-233
Investigating the solution space for online iterative explanation in goal reasoning agents
Goal Reasoning (GR) agents operating in partially observable environments need to hypothesize about hidden features in the current state to select an appropriate goal and create a plan to achieve it. The problem Online Iterative Explanation (OIE) is
- 2 March 2018
- Published by SAGE Publications in AI Communications
- Vol. 31 (2) , 213-233
Investigating the solution space for online iterative explanation in goal reasoning agents
Goal Reasoning (GR) agents operating in partially observable environments need to hypothesize about hidden features in the current state to select an appropriate goal and create a plan to achieve it. The problem Online Iterative Explanation (OIE) is
- 2 March 2018
- Published by SAGE Publications in AI Communications
- Vol. 31 (2) , 181-195
Distributed discrepancy detection for a goal reasoning agent in beyond-visual-range air combat
We describe an extension of the Tactical Battle Manager , which uses goal reasoning techniques to control unmanned air vehicles in simulated scenarios of beyond-visual-range air combat. Our prior work with the Tactical Battle Manager focused primaril
- 2 March 2018
- Published by SAGE Publications in AI Communications
- Vol. 31 (2) , 181-195
Distributed discrepancy detection for a goal reasoning agent in beyond-visual-range air combat
We describe an extension of the Tactical Battle Manager , which uses goal reasoning techniques to control unmanned air vehicles in simulated scenarios of beyond-visual-range air combat. Our prior work with the Tactical Battle Manager focused primaril
- 2 March 2018
- Published by SAGE Publications in AI Communications
- Vol. 31 (2) , 151-166
Goal reasoning for autonomous underwater vehicles: Responding to unexpected agents
We describe preliminary work toward applying a goal reasoning agent for controlling an underwater vehicle in a partially observable, dynamic environment. In initial at-sea tests, our investigation focuses on a notional scenario wherein an autonomous
- 2 March 2018
- Published by SAGE Publications in AI Communications
- Vol. 31 (2) , 151-166
Goal reasoning for autonomous underwater vehicles: Responding to unexpected agents
We describe preliminary work toward applying a goal reasoning agent for controlling an underwater vehicle in a partially observable, dynamic environment. In initial at-sea tests, our investigation focuses on a notional scenario wherein an autonomous
- 12 July 2017
- Published by SAGE Publications in AI Communications
- Vol. 30 (3-4) , 281-294
Using explanations to provide transparency during trust-guided behavior adaptation1
A robot that is a member of a human-robot team needs to not only perform its assigned tasks efficiently but also in a manner that human teammates find trustworthy. By maintaining adequate trust, the robot can prevent underutilization, disuse, and exc
- 12 July 2017
- Published by SAGE Publications in AI Communications
- Vol. 30 (3-4) , 281-294
Using explanations to provide transparency during trust-guided behavior adaptation1
A robot that is a member of a human-robot team needs to not only perform its assigned tasks efficiently but also in a manner that human teammates find trustworthy. By maintaining adequate trust, the robot can prevent underutilization, disuse, and exc
- Open Access
Cost-Optimal Algorithms for Planning with Procedural Control Knowledge
There is an impressive body of work on developing heuristics and other reasoning algorithms to guide search in optimal and anytime planning algorithms for classical planning. However, very little effort has been directed towards developing analogous techniques to guide search towards high-quality solutions in hierarchical planning formalisms like HTN planning, which allows using additional domain-specific procedural control knowledge. In lieu of such techniques, this control knowledge often needs to provide the necessary search guidance to the planning algorithm, which imposes a substantial burden on the domain author and can yield brittle or error-prone domain models. We address this gap by extending recent work on a new hierarchical goal-based planning formalism called Hierarchical Goal Network (HGN) Planning to develop the Hierarchically-Optimal Goal Decomposition Planner (HOpGDP), an HGN planning algorithm that computes hierarchically-optimal plans. HOpGDP is guided by $h_{HL}$, a new HGN planning heuristic that extends existing admissible landmark-based heuristics from classical planning to compute admissible cost estimates for HGN planning problems. Our experimental evaluation across three benchmark planning domains shows that HOpGDP compares favorably to both optimal classical planners due to its ability to use domain-specific procedural knowledge, and a blind-search version of HOpGDP due to the search guidance provided by $h_{HL}$.Open AccessCost-Optimal Algorithms for Planning with Procedural Control Knowledge
There is an impressive body of work on developing heuristics and other reasoning algorithms to guide search in optimal and anytime planning algorithms for classical planning. However, very little effort has been directed towards developing analogous techniques to guide search towards high-quality solutions in hierarchical planning formalisms like HTN planning, which allows using additional domain-specific procedural control knowledge. In lieu of such techniques, this control knowledge often needs to provide the necessary search guidance to the planning algorithm, which imposes a substantial burden on the domain author and can yield brittle or error-prone domain models. We address this gap by extending recent work on a new hierarchical goal-based planning formalism called Hierarchical Goal Network (HGN) Planning to develop the Hierarchically-Optimal Goal Decomposition Planner (HOpGDP), an HGN planning algorithm that computes hierarchically-optimal plans. HOpGDP is guided by $h_{HL}$, a new HGN planning heuristic that extends existing admissible landmark-based heuristics from classical planning to compute admissible cost estimates for HGN planning problems. Our experimental evaluation across three benchmark planning domains shows that HOpGDP compares favorably to both optimal classical planners due to its ability to use domain-specific procedural knowledge, and a blind-search version of HOpGDP due to the search guidance provided by $h_{HL}$. - 13 November 2014
- Published by Springer Nature in Automated Software Engineering
- Vol. 22 (2) , 159-197
Building high assurance human-centric decision systems
- 13 November 2014
- Published by Springer Nature in Automated Software Engineering
- Vol. 22 (2) , 159-197
Building high assurance human-centric decision systems
- 26 February 2013
- Published by Elsevier in Artificial Intelligence
- Vol. 199-200, 106-121
Multiparticipant chat analysis: A survey
- 26 February 2013
- Published by Elsevier in Artificial Intelligence
- Vol. 199-200, 106-121
Multiparticipant chat analysis: A survey