1 Jan

Case-Based Learning from Proactive Communication

Posted by cognitivecomputing in Agents, Learning. Tagged: , .

We present a proactive communication approach that allows CBR agents to gauge the strengths and weaknesses of other CBR agents. The communication protocol allows CBR agents to learn from communicating with other CBR agents in such a way that each agent is able to retain certain cases provided by other agents that are able to improve their individual performance (without need to disclose all the contents of each case base). The selection and retention of cases is modeled as a case bartering process, where each individual CBR agent autonomously decides which cases offers for bartering and which offered barters accepts. Experimental evaluations show that the sum of all these individual decisions result in a clear improvement in individual CBR agent performance with only a moderate increase of individual case bases.

Read the paper:

Case-Based Learning from Proactive Communication

by Santi Ontañón and Enric Plaza

International Joint Conference on Artificial Intelligence (IJCAI 2007), pp. 999-1004
www.cc.gatech.edu/faculty/ashwin/papers/er-07-18.pdf

27 Jul

A Synapse Plasticity Model for Conceptual Drift Problems

Posted by cognitivecomputing in Learning. Tagged: .

Traditional supervised learning techniques do not address online learning problems such as concept drift, due to the fact that learning is offine when using these methods. Associative neural networks using Hebbian learning rules show robust performance in classification tasks involving concept drift. Biologically plausible neural networks represent a set of computational models designed to be more strongly related to biological neuron models. In this paper, we apply a biologically inspired plasticity model of synapse dynamics to a concept drift classification problem. The motivation for this method is to provide more biologically plausible networks in cognitive tasks.

Read the paper:

A Synapse Plasticity Model for Conceptual Drift Problems

by Chip Mappus, Ashwin Ram

28th Annual Conference of the Cognitive Science Society (CogSci-06), Vancouver, BC, July 2006
www.cc.gatech.edu/faculty/ashwin/papers/er-06-01.pdf

15 May

CaseBook: A Problem-Based Learning Online Environment For High School Microbiology

Posted by cognitivecomputing in Education, Learning, Web / Web 2.0. Tagged: , .

Problem-based learning (PBL) is an educational approach that allows students to improve problem solving and critical thinking skills while learning science. However, PBL requires significant teacher time and expertise to develop problems and facilitate small-group problem-solving sessions. With advances in technology, PBL can be used in today’s classrooms in an effective and scalable manner.

CaseBook is an interactive computer system that allows for easy integration of PBL into the K-16 curriculum. Through a simple web-based interface, teachers enter and edit their case materials. As students work through cases, CaseBook guides them through a 3-stage process in which they analyze, learn and reflect. Students may work independently, or a small group of students may work together and share a Team Notebook, which is used to record facts, ideas, and issues about the case as they progress. Students assess their progress through self and group reflection and through teacher feedback.

We report on the use of CaseBook for a microbiology case in a high school classroom. The results suggest that CaseBook is effective for both advanced and remedial students. As the technological capacity of students and classrooms increase, it is only appropriate to use this technology to implement novel methods of teaching that will provide students the skills they need post- graduation.

Read the paper:

CaseBook: A Problem-Based Learning Online Environment For High School Microbiology

by JL Holzman, G Louizi, SC Fowler, E Lindsey, JJ Harrigan, P Ram, A Ram

12th American Society for Microbiology (ASM) Conference for Undergraduate Educators, Atlanta, GA, May 2006
www.cc.gatech.edu/faculty/ashwin/papers/er-05-06.doc.pdf
www.cc.gatech.edu/faculty/ashwin/papers/er-05-06.pdf

1 Oct

Text Mining Biomedical Literature for Discovering Gene-to-Gene Relationships

Posted by cognitivecomputing in Health & Wellness, Language. Tagged: , , .

Partitioning closely related genes into clusters has become an important element of practically all statistical analyses of microarray data. A number of computer algorithms have been developed for this task. Although these algorithms have demonstrated their usefulness for gene clustering, some basic problems remain. This paper describes our work on extracting functional keywords from MEDLINE for a set of genes that are isolated for further study from microarray experiments based on their differential expression patterns. The sharing of functional keywords among genes is used as a basis for clustering in a new approach called BEA-PARTITION. Functional keywords associated with genes were extracted from MEDLINE abstracts. We modified the Bond Energy Algorithm (BEA), which is widely accepted in psychology and database design but is virtually unknown in bioinformatics, to cluster genes by functional keyword associations.

The results showed that BEA-PARTITION and hierarchical clustering algorithm outperformed k-means clustering and self-organizing map by correctly assigning 25 of 26 genes in a test set of four known gene groups. To evaluate the effectiveness of BEA-PARTITION for clustering genes identified by microarray profiles, 44 yeast genes that are differentially expressed during the cell cycle and have been widely studied in the literature were used as a second test set. Using established measures of cluster quality, the results produced by BEA-PARTITION had higher purity, lower entropy, and higher mutual information than those produced by k-means and self-organizing map. Whereas BEA-PARTITION and the hierarchical clustering produced similar quality of clusters, BEA-PARTITION provides clear cluster boundaries compared to the hierarchical clustering. BEA-PARTITION is simple to implement and provides a powerful approach to clustering genes or to any clustering problem where starting matrices are available from experimental observations.

Text Mining Biomedical Literature for Discovering Gene-to-Gene Relationships

by Ying Liu, Sham Navathe, Jorge Civera, Venu Dasigi, Ashwin Ram, Brian Ciliax, Ray Dingledine

IEEE/ACM Transactions on Computational Biology and Bioinformatics,2(4):380-384, Oct-Dec 2005
www.cc.gatech.edu/faculty/ashwin/papers/er-05-01.pdf

9 Jun

From Student Learner to Professional Learner: Training for Lifelong Learning through Online PBL

Posted by cognitivecomputing in Education, Learning. Tagged: , .

Problem-based learning (PBL) is a constructivist pedagogy in which students learn science and develop critical thinking skills by solving real-world problems in small groups. Studies have shown that PBL students are more motivated and become better learners. However, this pedagogy places additional demands on faculty. It takes time and expertise to develop suitable problems, to coach students, and to facilitate problem-solving sessions.

We are developing interactive computer systems incorporating the PBL approach which (1) help teachers design, enter, and share problems, and (2) support students and guide them through the PBL inquiry process and (3) assist teachers to continue their professional development by improving their domain knowledge. System development is guided by K-16 educators and tested in classrooms. Our goal is to enable educators to adopt this pedagogy in K-16 classrooms with minimal overhead and to assist them to effortlessly learn new technologies and new material.

Read the paper:

From Student Learner to Professional Learner: Training for Lifelong Learning through Online PBL

by Preetha Ram, Ashwin Ram, Chris Sprague

International Conference on Problem-Based Learning (PBL-05), Lahti, Finland, June 2005
www.cc.gatech.edu/faculty/ashwin/papers/er-05-03.pdf

15 May

Case-Based Reasoning for Gas Turbine Diagnostics

Posted by cognitivecomputing in Learning. Tagged: , , .

General Electric used case-based reasoning for gas turbine diagnostics at their monitoring and diagnostics center in Atlanta, GA. This application had requirements that included accuracy, maintainability, modularity, parameterization, robustness, and integration of the system into an existing infrastructure. The CBR system has a modular “plug and play” architecture to facilitate experimentation and optimization. It was integrated into the production environment in 2004. The CBR system is currently in a trial deployment where diagnoses made by the system are created along with the previous process of using human-generated diagnosis.

Case-Based Reasoning for Gas Turbine Diagnostics

by Mark Devaney, Bill Cheetham

18th International FLAIRS Conference (FLAIRS-05), Clearwater, FL, May 2005
www.cc.gatech.edu/faculty/ashwin/papers/er-05-05.pdf

1 Apr

Preventing Failures by Mining Maintenance Logs with Case-Based Reasoning

Posted by cognitivecomputing in Language, Learning. Tagged: , .

The project integrates work in natural language processing, machine learning, and the semantic web, bringing together these diverse disciplines in a novel way to address a real problem. The objective is to extract and categorize machine components and subsystems and their associated failures using a novel approach that combines text analysis, unsupervised text clustering, and domain models. Through industrial partnerships, this project will demonstrate effectiveness of the proposed approach with actual industry data.

Read the paper:

Preventing Failures by Mining Maintenance Logs with Case-Based Reasoning

by Mark Devaney, Ashwin Ram, Hai Qui, Jay Lee

59th Meeting of the Society for Machinery Failure Prevention Technology (MFPT-59), Virginia Beach, VA, April 2005
www.cc.gatech.edu/faculty/ashwin/papers/er-05-04.pdf

1 Jan

Interactive Case-Based Reasoning for Precise Information Retrieval

Posted by cognitivecomputing in Language, Learning, Web / Web 2.0. Tagged: , , , .

The knowledge explosion has continued to outpace technological innovation in search engines and knowledge management systems. It is increasingly difficult to find relevant information, not just on the World Wide Web at large but even in domain- specific medium-sized knowledge bases—online helpdesks, maintenance records, technical repositories, travel databases, e-commerce sites, and many others. Despite advances in search and database technology, the average user still spends inordinate amounts of time looking for specific information needed for a given task.

This paper describes an adaptive system for the precise, rapid retrieval and synthesis of information from medium-sized knowledge bases in response to problem-solving queries from a diverse user population. We advocate a shift in perspective from “search” to “answers. Instead of returning dozens or hundreds of hits to a user, the system should attempt to find answers that may or may not match the query directly but are relevant to the user’s problem or task.

This problem has been largely overlooked as research has tended to concentrate on techniques for broad searches of large databases over the Internet (as exemplified by Google) and structured queries of well-defined databases (as exemplified by SQL). However, the problem discussed in this chapter is sufficiently different from these extremes to both present a novel set of challenges as well as provide a unique opportunity to apply techniques not traditionally found in the information retrieval literature. Specifically, we discuss an innovative combination of techniques‚ case-based reasoning coupled with text analytics‚ to solve the problem in a practical, real-world context.

We are interested in applications in which users must quickly retrieve answers to specific questions or problems from a complex information database with a minimum of effort and interaction. Examples include internal helpdesk support, web-based self-help for consumer products, decision-aiding systems for support personnel, and repositories for specialized documents such as patents, technical documents, or scientific literature. These applications are characterized by the fact that a diverse user population accesses highly focused knowledge bases in order to find precise answers to specific questions or problems. Despite the growing popularity of on-line service and support facilities for internal use by employees and for external use for customers, most such sites rely on traditional search engine technologies and are not very effective in reducing the time, expertise, and complexity required on the user’s part.

Read the paper:

Interactive Case-Based Reasoning for Precise Information Retrieval

by Ashwin Ram, Mark Devaney

In Case-Based Reasoning in Knowledge Discovery and Data Mining, David Aha and Sankar Pal (editors). 
www.cc.gatech.edu/faculty/ashwin/papers/er-05-02.pdf

15 May

Plan Recognition in Large-Scale Multi-Agent Tactical Domains

Posted by cognitivecomputing in Learning. Tagged: , .

This research addresses the task of representing and recognizing events in a tactical domain from large-scale spatio-temporal data under conditions of limited observability and high noise with real-time response constraints.  These assumptions differ from those traditionally made in  plan recognition and produce a problem that combines aspects of plan recognition, pattern recognition and object tracking. This research provides evidence that parsimonious qualitative representations used to represent pair-wise interactions among agents can be combined to identify large-scale group behaviors that form the basis of increasingly complex patterns of activity.

A comprehensive software application was constructed to demonstrate the claims of the thesis by evaluating performance on a real-world problem involving the recognition of a tactical maneuver in actual US Army training battles.  Evaluations were conducted and performance evaluated by both novices and active military subject matter experts.

Plan Recognition in Large-Scale Multi-Agent Tactical Domains

by Mark Devaney

PhD Thesis, College of Computing, Georgia Institute of Technology, Atlanta, GA, 2003
www.cc.gatech.edu/faculty/ashwin/papers/git-cc-03-01.ps.zip

1 Mar

Scaling Spreading Activation for Information Retrieval

Posted by cognitivecomputing in Language, Web / Web 2.0. Tagged: , , .

The Information Retrieval Intelligent Assistant (IRIA) project applies principles of memory retrieval from cognitive science to the problem of information retrieval from large heterogeneous databases. IRIA uses spreading activation over a semantic network for information retrieval, a technique which has proven effective in a variety of tasks. However, some of the very features which motivated the choice of spreading activation for information retrieval — such the use of fanout to automatically compute term weights, or the use of thresholds to automatically limit computation spent on irrelevant items — can introduce new problems as systems are scaled to larger sizes.

This paper discusses the use of semantic networks and spreading activation for information retrieval in the context of the IRIA approach, reviews some of the problems that arise as these technologies are scaled up to production systems, presents some preliminary results that illustrate these problems in practice, and discusses potential solutions.

Read the paper:

Scaling Spreading Activation for Information Retrieval

by Anthony Francis, Mark Devaney, Juan Santamaria, Ashwin Ram

International Conference on Artificial Intelligence (ICAI-01), Las Vegas, Nevada, March 2001
www.cc.gatech.edu/faculty/ashwin/papers/er-01-01.pdf
« Older Entries
Newer Entries »