A5056481909- AI-based Problem Solving and Planning
- Logic, Reasoning, and Knowledge
- Semantic Web and Ontologies
- Educational Systems and Policies
- Topic Modeling
- Diverse Topics in Contemporary Research
- Religion, Society, and Development
- Reinforcement Learning in Robotics
- Advancements in Battery Materials
- Christian Theology and Mission
- Robot Manipulation and Learning
- Supercapacitor Materials and Fabrication
- Multimodal Machine Learning Applications
- Robotics and Automated Systems
- Human Pose and Action Recognition
- Pentecostalism and Christianity Studies
- Intelligent Tutoring Systems and Adaptive Learning
- Advanced Battery Materials and Technologies
- Advanced Vision and Imaging
- Spacecraft and Cryogenic Technologies
- Multi-Agent Systems and Negotiation
- Computability, Logic, AI Algorithms
- Domain Adaptation and Few-Shot Learning
- Cognitive Science and Mapping
- Natural Language Processing Techniques
University of British Columbia
2013-2024
Institute of High Performance Computing
2021-2024
Agency for Science, Technology and Research
2021-2024
Hallym University
2020-2023
Hallym Polytechnic University
2021-2023
Hallym University Medical Center
2022
Stanford University
2004-2021
University of Kansas
2015-2020
Gangneung–Wonju National University
2018
Daewoo Shipbuilding and Marine Engineering (South Korea)
2011-2016
As intelligent agents become more autonomous, sophisti- cated, and prevalent, it becomes increasingly important that humans interact with them effectively. Machine learning is now used regularly to acquire expertise, but common techniques produce opaque content whose behavior difficult interpret. Before they will be trusted by humans, autonomous must able explain their decisions the reasoning produced choices. We refer this general ability as explainable agency. This capacity for explaining...
Event extraction is an important task in natural language processing that focuses on mining event-related information from unstructured text. Despite considerable advancements, it still challenging to achieve satisfactory performance this task, and issues like data scarcity imbalance obstruct progress. In paper, we introduce innovative approach where employ Large Language Models (LLMs) as expert annotators for event extraction. We strategically include sample the training dataset prompt a...
In this paper, we present a principled approach to constructing believable game players that relies on cognitive architecture. The resulting agent is capable of playing the \uc/ in plausible manner when faced with similar situations as its human counterparts. We discuss how architectural features like goal-directed but reactive execution and incremental learning can produce more synthetic characters.
In this paper we describe ICARUS, an integrated architecture for intelligent physical agents. The framework supports long-term memories hierarchical concepts and skills, along with mechanisms recognizing that hold in the environment, determining which skills are applicable, selecting execution skill highest expected value. We illustrate these processes examples from domain of in-city driving, report experimental studies on a package-delivery task examine ICARUS' ability to combine reactive...
Summary Sustained and increasing world energy demands have led to very high oil prices. In parallel, there has been a significant increase in interest economic environmentally sensitive solutions for the monetization of remote, stranded gas offshore. Current global natural-gas reserves total approximately 6,100 Tcf, according US Energy Information Administration estimates. Roughly one-half these are considered be that is uneconomical market delivery because remote location potential markets,...