We present a framework for learning comprehensible models of sequential decision tasks in which agent strategies are characterized using temporal logic formulas.
Publications
The Role of California’s County Offices of Education and Implications for Arts Education
This study describes the COE role in arts education, examines how COE activities have shifted in response to California’s Local Control Funding Formula, and examines how these changes may affect access, participation, quality, and equity in arts education in K-12 schools.
Experimental Evaluation of Subject Matter Expert-Oriented Knowledge Base Authoring Tools
We describe a large-scale experiment in which non-artificial intelligence subject matter experts (SMEs)—with neither artificial intelligence background nor extensive training in the task—author knowledge bases (KBs) following a challenge problem specification with a strong question-answering component.
Towards Understanding Confusion and Affective States Under Communication Failures in Voice-Based Human-Machine Interaction
We present a series of two studies conducted to understand user’s affective states during voice-based human-machine interactions. Emphasis is placed on the cases of communication errors or failures.
Incremental Learning with Differentiable Architecture and Forgetting Search
In this paper, we show that leveraging NAS for incremental learning results in strong performance gains for classification tasks.
Outcome-Guided Counterfactuals for Reinforcement Learning Agents from a Jointly Trained Generative Latent Space
We present a novel generative method for producing unseen and plausible counterfactual examples for reinforcement learning (RL) agents based upon outcome variables that characterize agent behavior.
Antiviral T-cell Biofactory platform for SARS-CoV-2
We engineered a T cell to synthesize interferons (IFNs) as antiviral proteins upon recognizing the virus envelop protein of SARS-CoV-2, i.e., anti-SARS T-cell Biofactory.
Saccade Mechanisms for Image Classification, Object Detection and Tracking
We examine how the saccade mechanism from biological vision can be used to make deep neural networks more efficient for classification and object detection problems. Our proposed approach is based on the ideas of attention-driven visual processing and saccades, miniature eye movements influenced by attention.
A virtual reality-based mind–body approach to downregulate psychophysiological arousal in adolescent insomnia
A novel, digital, immersive virtual reality (VR)-based mind–body approach, designed to reduce bedtime arousal in adolescents with insomnia.