Christopher J. MacLellan
YOU?
Author Swipe
View article: When Should Users Check? A Decision-Theoretic Model of Confirmation Frequency in Multi-Step AI Agent Tasks
When Should Users Check? A Decision-Theoretic Model of Confirmation Frequency in Multi-Step AI Agent Tasks Open
Existing AI agents typically execute multi-step tasks autonomously and only allow user confirmation at the end. During execution, users have little control, making the confirm-at-end approach brittle: a single error can cascade and force a…
View article: Improving Public Service Chatbot Design and Civic Impact: Investigation of Citizens’ Perceptions of a Metro City 311 Chatbot
Improving Public Service Chatbot Design and Civic Impact: Investigation of Citizens’ Perceptions of a Metro City 311 Chatbot Open
As governments increasingly adopt digital tools, public service chatbots have emerged as a growing communication channel. This paper explores the design considerations and engagement opportunities of public service chatbots, using a 311 ch…
View article: Decomposed Inductive Procedure Learning: Learning Academic Tasks with Human-Like Data Efficiency
Decomposed Inductive Procedure Learning: Learning Academic Tasks with Human-Like Data Efficiency Open
Human learning relies on specialization -- distinct cognitive mechanisms working together to enable rapid learning. In contrast, most modern neural networks rely on a single mechanism: gradient descent over an objective function. This rais…
View article: TutorGym: A Testbed for Evaluating AI Agents as Tutors and Students
TutorGym: A Testbed for Evaluating AI Agents as Tutors and Students Open
Recent improvements in large language model (LLM) performance on academic benchmarks, such as MATH and GSM8K, have emboldened their use as standalone tutors and as simulations of human learning. However, these new applications require more…
View article: Model Human Learners: Computational Models to Guide Instructional Design
Model Human Learners: Computational Models to Guide Instructional Design Open
Instructional designers face an overwhelming array of design choices, making it challenging to identify the most effective interventions. To address this issue, I propose the concept of a Model Human Learner, a unified computational model …
View article: TRESTLE: A Model of Concept Formation in Structured Domains
TRESTLE: A Model of Concept Formation in Structured Domains Open
The literature on concept formation has demonstrated that humans are capable of learning concepts incrementally, with a variety of attribute types, and in both supervised and unsupervised settings. Many models of concept formation focus on…
View article: Improving Interface Design in Interactive Task Learning for Hierarchical Tasks based on a Qualitative Study
Improving Interface Design in Interactive Task Learning for Hierarchical Tasks based on a Qualitative Study Open
Interactive Task Learning (ITL) systems acquire task knowledge from human instructions in natural language interaction. The interaction design of ITL agents for hierarchical tasks stays uncharted. This paper studied Verbal Apprentice Learn…
View article: Evaluating Alternative Training Interventions Using Personalized Computational Models of Learning
Evaluating Alternative Training Interventions Using Personalized Computational Models of Learning Open
Evaluating different training interventions to determine which produce the best learning outcomes is one of the main challenges faced by instructional designers. Typically, these designers use A/B experiments to evaluate each intervention;…
View article: Towards Educator-Driven Tutor Authoring: Generative AI Approaches for Creating Intelligent Tutor Interfaces
Towards Educator-Driven Tutor Authoring: Generative AI Approaches for Creating Intelligent Tutor Interfaces Open
Intelligent Tutoring Systems (ITSs) have shown great potential in delivering\npersonalized and adaptive education, but their widespread adoption has been\nhindered by the need for specialized programming and design skills. Existing\napproa…
View article: The Impact of an XAI-Augmented Approach on Binary Classification with Scarce Data
The Impact of an XAI-Augmented Approach on Binary Classification with Scarce Data Open
Point-of-Care Ultrasound (POCUS) is the practice of clinicians conducting and interpreting ultrasound scans right at the patient's bedside. However, the expertise needed to interpret these images is considerable and may not always be prese…
View article: VAL: Interactive Task Learning with GPT Dialog Parsing
VAL: Interactive Task Learning with GPT Dialog Parsing Open
Machine learning often requires millions of examples to produce static, black-box models. In contrast, interactive task learning (ITL) emphasizes incremental knowledge acquisition from limited instruction provided by humans in modalities s…
View article: Apprentice Tutor Builder: A Platform For Users to Create and Personalize Intelligent Tutors
Apprentice Tutor Builder: A Platform For Users to Create and Personalize Intelligent Tutors Open
Intelligent tutoring systems (ITS) are effective for improving students' learning outcomes. However, their development is often complex, time-consuming, and requires specialized programming and tutor design knowledge, thus hindering their …
View article: Cobweb: An Incremental and Hierarchical Model of Human-Like Category Learning
Cobweb: An Incremental and Hierarchical Model of Human-Like Category Learning Open
Cobweb, a human-like category learning system, differs from most cognitive science models in incrementally constructing hierarchically organized tree-like structures guided by the category utility measure. Prior studies have shown that Cob…
View article: Interpretable Models for Detecting and Monitoring Elevated Intracranial Pressure
Interpretable Models for Detecting and Monitoring Elevated Intracranial Pressure Open
Detecting elevated intracranial pressure (ICP) is crucial in diagnosing and managing various neurological conditions. These fluctuations in pressure are transmitted to the optic nerve sheath (ONS), resulting in changes to its diameter, whi…
View article: Incremental Concept Formation over Visual Images Without Catastrophic Forgetting
Incremental Concept Formation over Visual Images Without Catastrophic Forgetting Open
Deep neural networks have excelled in machine learning, particularly in vision tasks, however, they often suffer from catastrophic forgetting when learning new tasks sequentially. In this work, we introduce Cobweb4V, an alternative to trad…
View article: VAL: Interactive Task Learning with GPT Dialog Parsing
VAL: Interactive Task Learning with GPT Dialog Parsing Open
Machine learning often requires millions of examples to produce static, black-box models. In contrast, interactive task learning (ITL) emphasizes incremental knowledge acquisition from limited instruction provided by humans in modalities s…
View article: MobilePTX: Sparse Coding for Pneumothorax Detection Given Limited Training Examples
MobilePTX: Sparse Coding for Pneumothorax Detection Given Limited Training Examples Open
Point-of-Care Ultrasound (POCUS) refers to clinician-performed and interpreted ultrasonography at the patient's bedside. Interpreting these images requires a high level of expertise, which may not be available during emergencies. In this p…
View article: Interactive Learning of Hierarchical Tasks from Dialog with GPT
Interactive Learning of Hierarchical Tasks from Dialog with GPT Open
We present a system for interpretable, symbolic, interactive task learning from dialog using a GPT model as a conversational front-end. The learned tasks are represented as hierarchical decompositions of predicate-argument structures with …
View article: Speculative Game Design of Asymmetric Cooperative Games to Study Human-Machine Teaming
Speculative Game Design of Asymmetric Cooperative Games to Study Human-Machine Teaming Open
While recent advances in Artificial Intelligence and Machine Learning have demonstrated the potential for AI systems to outperform human experts in many domains, including games, AI systems still generally lack the ability to team with hum…
View article: Allergic Polysensitization Clusters: Newly Recognized Severity Marker in Urban Asthmatic Adults
Allergic Polysensitization Clusters: Newly Recognized Severity Marker in Urban Asthmatic Adults Open
Introduction: While reliable, quantitative in vitro testing for sensitivity to aeroallergens has been available for decades, such information has largely been ignored in clustering analyses of asthma. Our aim is to explore allergic polysen…
View article: MobilePTX: Sparse Coding for Pneumothorax Detection Given Limited Training Examples
MobilePTX: Sparse Coding for Pneumothorax Detection Given Limited Training Examples Open
Point-of-Care Ultrasound (POCUS) refers to clinician-performed and interpreted ultrasonography at the patient's bedside. Interpreting these images requires a high level of expertise, which may not be available during emergencies. In this p…
View article: Modifying Deep Knowledge Tracing for Multi-step Problems
Modifying Deep Knowledge Tracing for Multi-step Problems Open
Previous studies suggest that Deep Knowledge Tracing (or DKT) has fundamental limitations that prevent it from supporting mastery learning on multi-step problems. Although DKT is quite accurate at predicting observed correctness in offline…
View article: (A)I Will Teach You to Play Gomoku: Exploring the Use of Game AI to Teach People
(A)I Will Teach You to Play Gomoku: Exploring the Use of Game AI to Teach People Open
Artificial intelligence systems such as AlphaGo, AlphaGo Zero and AlphaZero, have demonstrated their advantages and competency over human players. However, little research has explored the possibility of applying such algorithms for educat…
View article: Cluster Analysis of Allergic Poly-Sensitizations in Urban Adults with Asthma
Cluster Analysis of Allergic Poly-Sensitizations in Urban Adults with Asthma Open
Introduction While reliable, quantitative in vitro testing for sensitivity to aeroallergens has been available for decades, if and how asthma severity markers might be predictably expressed in clusters matched for comparable multiple sensi…
View article: Convolutional Cobweb: A Model of Incremental Learning from 2D Images
Convolutional Cobweb: A Model of Incremental Learning from 2D Images Open
This paper presents a new concept formation approach that supports the ability to incrementally learn and predict labels for visual images. This work integrates the idea of convolutional image processing, from computer vision research, wit…
View article: Supplementary Material for: Allergic Polysensitization Clusters: Newly Recognized Severity Marker in Urban Asthmatic Adults
Supplementary Material for: Allergic Polysensitization Clusters: Newly Recognized Severity Marker in Urban Asthmatic Adults Open
Introduction: While reliable, quantitative in vitro testing for sensitivity to aeroallergens has been available for decades, such information has largely been ignored in clustering analyses of asthma. Our aim is to explore allergic polysen…
View article: Decomposed Inductive Procedure Learning
Decomposed Inductive Procedure Learning Open
Recent advances in machine learning have made it possible to train artificially intelligent agents that perform with super-human accuracy on a great diversity of complex tasks. However, the process of training these capabilities often nece…