(Georgia Institute of Technology, 2023-04-13)
MacLellan, Christopher J.
The AI community has made significant strides in developing artificial systems with human-level proficiency across various tasks. However, the learning processes in most systems differ vastly from human learning, often being substantially less efficient and flexible. For instance, training large language models demands massive amounts of data and power, and updating them with new information remains challenging. In contrast, humans employ highly efficient incremental learning processes to continually update their knowledge, enabling them to acquire new knowledge with minimal examples and without overwriting prior learning. In this talk, I will discuss some of the key learning capabilities humans exhibit and present three research vignettes from my lab that explore the development of computational systems with these capabilities. The first two vignettes explore computational models of skill learning from worked examples, correctness feedback, and verbal instruction. The third vignette investigates computational models of concept formation from natural language corpora. In conclusion, I will discuss future research directions and a broader vision for how cognitive science and cognitive systems research can lead to new AI advancements.
(Georgia Institute of Technology, 2009)
Shah, Hina; Görg, Carsten; Harrold, Mary Jean
This paper presents a new visualization technique for supporting the understanding of exception-handling constructs in
Java programs. To understand the requirements for such a visualization, we surveyed a group of software developers, and
used the results of that survey to guide the creation of the visualizations. The technique presents the exception-handling
information using three views: the quantitative view, the flow view, and the contextual view. The quantitative view provides a
high-level view that shows the throw-catch interactions in the program, along with relative numbers of these interactions, at
the package level, the class level, and the method level. The flow view shows the type-throw-catch interactions, illustrating
information such as which exception types reach particular throw statements, which catch statements handle particular
throw statements, and which throw statements are not caught in the program. The contextual view shows, for particular
type-throw-catch interactions, the packages, classes, and methods that contribute to that exception-handling construct. We
implemented our technique in an Eclipse plugin called EnHanCe and conducted a usability and utility study with participants
in industry.