Person:

Goel, Ashok K.

Permanent Link

https://hdl.handle.net/1853/71296

Associated Organization(s)

Organizational Unit

School of Computational Science and Engineering

Full item page

Publication Search Results

Now showing 1 - 8 of 8

A virtual coach for question asking and enabling learning by reflection in startup engineering

(Georgia Institute of Technology, 2020-12) Goel, Ashok K. ; Hong, Sung Jae ; Kuthalam, Mukundan ; Arcalgud, Arup ; Gulati, Siddharth ; Howe, James ; Karnati, Nikhita ; Mardis, Aaron ; Ro, Jae ; McGreggor, Keith

The Socratic method of teaching engages learners in extended conversations and encourages learning through answering questions, making arguments, and reflecting on the evolving conversation. This method can be a powerful instrument of learning by reflection, especially in domains in which the right answers to open questions are not known in advance such as entrepreneurship. In this paper, we describe an initial experiment in developing AI technology for simulating the Socratic method of teaching in learning about entrepreneurship. When a would-be entrepreneurs creates a business model on the Business Model Canvas (BMC), the AI agent named Errol uses semantic and lexical analysis of the entries on the BMC to ask questions of the students. By attempting to categorize and correct the errors that novices typically make, Errol seeks to accelerate the process by which a novice can start creating more expert-like business models
Jill Watson: A Virtual Teaching Assistant for Online Education

(Georgia Institute of Technology, 2016) Goel, Ashok K. ; Polepeddi, Lalith

MOOCs are rapidly proliferating. However, for many MOOCs, the effectiveness of learning is questionable and student retention is low. One recommendation for improving the learning and the retention is to enhance the interaction between the teacher and the students. However, the number of teachers required to provide learning assistance to all students enrolled in all MOOCs is prohibitively high. One strategy for improving interactivity in MOOCs is to use virtual teaching assistants to augment and amplify interaction with human teachers. We describe the use of a virtual teaching assistant called Jill Watson (JW) for the Georgia Tech OMSCS 7637 class on Knowledge-Based Artificial Intelligence. JW has been operating on the online discussion forums of different offerings of the KBAI class since Spring 2016. By now some 750 students have interacted with different versions of JW. In the latest, Spring 2017 offering of the KBAI class, JW autonomously responded to student introductions, posted weekly announcements, and answered routine, frequently asked questions. In this article, we describe the motivations, background, and evolution of the virtual question-answering teaching assistant.
An Experiment in Teaching Cognitive Systems Online

(Georgia Institute of Technology, 2015) Goel, Ashok K. ; Joyner, David A.

In Fall 2014 we offered an online course CS 7637 Knowledge-Based Artificial Intelligence: Cognitive Systems (KBAI) to about 200 students as part of the Georgia Tech Online MS in CS program. We incorporated lessons from learning science into the design of the project-based online KBAI course. We embedded ~150 microexercises and ~100 AI nanotutors into the online videos. As a quasi-experiment, we ran a typical inperson class with 75 students in parallel, with the same course syllabus, structure, assignments, projects and examinations. Based on the feedback of the students in the online KBAI class, and comparison of their performance with the students in the inperson class, the online course appears to have been a success. In this paper, we describe the design, development and delivery of the online KBAI class. We also discuss the evaluation of the course.
SoD-TEAM: Teleological reasoning in adaptive software design

(Georgia Institute of Technology, 8/31/2012) Goel, Ashok K. ; Rugaber, Spencer
Using Spatial Structure in the Associative Retrieval of 2-D Line Drawings

(Georgia Institute of Technology, 2002) Yaner, Patrick W. ; Goel, Ashok K.

We consider the problem of associative image retrieval, focusing on retrieval of 2-D line drawings by example. We represent 2-D line drawings as semantic networks of spatial elements and relations among them. We describe a process for retrieving the drawings based on a structural analogy between the query and the stored images. We then present several methods of retrieving the drawings: the first family methods uses logical unification and resolution to accomplish the matching; the second family of methods heuristically prunes the stored drawings and then does the resolution and unification on the remaining drawings; two more methods treat the retrieval problem as a constraint satisfaction problem and use common CSP techniques for solving it; and the last two methods combine the heuristic step of the second method with the CSP technique of the third and fourth. We report on experimental results that compare the performance of these methods on computer-based libraries of drawings. A surprising result of our work is that for the fastest of these methods two stage retrieval appeared to offer no benefit over one stage retrieval.
Model-Based Reconfiguration of Schema-Based Reactive Control Architectures

(Georgia Institute of Technology, 1997) Chen, Zhong ; Goel, Ashok K. ; Rowland, Paul ; Stroulia, Eleni

Reactive methods of control get caught in local minima. Fortunately schema-based reactive control systems have built-in redundancy that enables multiple configurations with different modes. We describe a model-based method that exploits this redundancy, and, under certain conditions, reconfigures schema-based reactive control systems trapped in behavioral cycles due to the presence of local minima. The qualitative model specifies the functions and modes of the perceptual and motor schemas, and represents the reactive architecture as a structure-behavior-function model. The model-based method monitors the reactive processing, detects failures in the form of behavioral cycles, analyzes the processing trace, identifies potential modifications, and reconfigures the reactive architecture. We report on experiments with a simulated robot navigating a complex space.
Some Experimental Results in Multistrategy Navigation Planning

(Georgia Institute of Technology, 1995) Goel, Ashok K. ; Ali, Khaled Subhi ; Stroulia, Eleni

Spatial navigation is a classical problem in AI. In the paper, we examine three specific hypotheses regarding multistrategy navigation planning in visually engineered physical spaces containing discrete pathways: (1) For Hybrid robots capable of both deliberative planning and situated action, qualitative representations of topological knowledge are sufficient for enabling effective spatial navigation; (2) For deliberative planning, the case-based strategy of plan reuse generates plans more efficiently than the model-based strategy of search without any loss in the quality of plans or problem-solving coverage; and (3) For the strategy of model-based search, the “principle of locality” provides a productive basis for partitioning and organizing topological knowledge. We describe the design of a multistrategy navigation planner called Router that provides an experimental testbed for evaluation the three hypotheses. We also describe the embodiment of Router on a mobile robot called Stimpy for testing the first hypothesis. Experiments with Stimpy indicate that this hypothesis apparently is valid for hybrid robots in visually engineered spaces containing discrete pathways such as office buildings. In addition, two different kinds of simulation experiments with Router indicate that the second and the third hypotheses are only partially correct. Finally, we relate the evaluation methods and experimental designs with the research hypotheses.
Reasoning About Function in Reflective Systems

(Georgia Institute of Technology, 1993) Stroulia, Eleni ; Goel, Ashok K.

Functional models have been extensively investigated in the context of several problem-solving tasks such as device diagnosis and design. In this paper, we view problem solvers themselves as devices, use functional models to represent how they work, and subsequently employ these models for performance-driven reflective reasoning and learning. We represent the functioning of a problem solver as a structure-behavior-function model that specifies how the knowledge and reasoning of the problem solver results in the achievement of its goals. We view performance-driven learning as the task of redesigning the knowledge and reasoning of the problem solver. We use the structure-behavior-function model of the problem solver to monitor its reasoning, reflectively assign blame when it fails, and redesign its knowledge and reasoning. This paper describes an architecture for reflective model-based reasoning that is capable of a broad range of learning tasks. It also illustrates reflective model-based learning using examples from the Autognostic system, a reflective path planner.