no code implementations • 6 Mar 2024 • Xin Lian, Sashank Varma, Christopher J. MacLellan
Cobweb, a human like category learning system, differs from other incremental categorization models in constructing hierarchically organized cognitive tree-like structures using the category utility measure.
no code implementations • 4 Mar 2024 • Darryl Hannan, Steven C. Nesbit, Ximing Wen, Glen Smith, Qiao Zhang, Alberto Goffi, Vincent Chan, Michael J. Morris, John C. Hunninghake, Nicholas E. Villalobos, Edward Kim, Rosina O. Weber, Christopher J. MacLellan
Detecting elevated intracranial pressure (ICP) is crucial in diagnosing and managing various neurological conditions.
no code implementations • 26 Feb 2024 • Nicki Barari, Xin Lian, Christopher J. MacLellan
Deep neural networks have excelled in machine learning, particularly in vision tasks, however, they often suffer from catastrophic forgetting when learning new tasks sequentially.
no code implementations • 2 Oct 2023 • Lane Lawley, Christopher J. MacLellan
By using LLMs only for specific tasks--such as predicate and argument selection--within an algorithmic framework, VAL reaps the benefits of LLMs to support interactive learning of hierarchical task knowledge from natural language.
no code implementations • 17 May 2023 • Lane Lawley, Christopher J. MacLellan
We present a system for interpretable, symbolic, interactive task learning from dialog using a GPT model as a conversational front-end.
no code implementations • 22 Dec 2022 • Christopher J. MacLellan, Peter Matsakis, Pat Langley
The framework builds on Cobweb, an early system for constructing taxonomic hierarchies of probabilistic concepts that used a tabular, attribute-value encoding of training cases and concepts, making it unsuitable for sequential input like language.
no code implementations • 6 Dec 2022 • Darryl Hannan, Steven C. Nesbit, Ximing Wen, Glen Smith, Qiao Zhang, Alberto Goffi, Vincent Chan, Michael J. Morris, John C. Hunninghake, Nicholas E. Villalobos, Edward Kim, Rosina O. Weber, Christopher J. MacLellan
Point-of-Care Ultrasound (POCUS) refers to clinician-performed and interpreted ultrasonography at the patient's bedside.
no code implementations • 18 Jan 2022 • Christopher J. MacLellan, Harshil Thakur
This paper presents a new concept formation approach that supports the ability to incrementally learn and predict labels for visual images.