Experiments with Safe μARTMAP : Effect of the network parameters on the network performance

Zhong, Mingyu; Rosander, Bryan; Georgiopoulos, Michael; Anagnostopoulos, Georgios C.; Mollaghasemi, Mansooreh; Richie, S.M.

doi:10.1016/j.neunet.2006.11.008

Cited by 8 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Journal papers co-authored by SMART undergraduate students include works on parallelization [32] and pipelining of Fuzzy ARTMAP [33], gap-based estimation [34] and experiments with micro-ARTMAP [35]. REU effort, involving 200 students, which results in a publication rate of 30% assuming that every student worked on a different project (see also [8]).…”

Section: B Ctml II Course Assessment and Evaluationmentioning

confidence: 99%

A Sustainable Model for Integrating Current Topics in Machine Learning Research Into the Undergraduate Curriculum

et al. 2009

Self Cite

View full text Add to dashboard Cite

Abstract-This paper presents an integrated research and teaching model that has resulted from an NSF-funded effort to introduce results of current Machine Learning research into the engineering and computer science curriculum at the University of Central Florida (UCF). While in-depth exposure to current topics in Machine Learning has traditionally occurred at the graduate level, the model developed affords an innovative and feasible approach to expanding the depth of coverage in research topics to undergraduate students. The model has been self-sustaining as evidenced by its continued operation during the years after the NSF grant's expiration, and is transferable to other institutions due to its use of modular and faculty-specific technical content. This model offers a tightly-coupled teaching and research approach to introducing current topics in Machine Learning research to undergraduates, while also involving them in the research process itself. The approach has provided new mechanisms to increase faculty participation in undergraduate research, has exposed approximately 15 undergraduates annually to research at UCF, and has effectively prepared a number of these students for graduate study through active involvement in the research process and co-authoring of publications.Index Terms-Curriculum development, integrated research and teaching, machine learning, team teaching models, undergraduate research experiences I. INTRODUCTION Current models of undergraduate research such as Research Experiences forUndergraduate Students (REU), Honors Theses, and senior-year projects frequently Manuscript received 28 September, 2007. This work was supported in part by the National Science Foundation grant #0203446. Corresponding author: M. Georgiopoulos 407-823-5338; fax: 407-823-5835; e-mail: michaelg@mail.ucf.edu 1 M. Georgiopoulos, R. F. DeMara, A. J. Gonzalez, A. S. Wu, M. Mollaghasemi, M. Kysilka, J. Secretan, and C. A. Sharma are with the University of Central Florida, Orlando, FL 32816 USA. 2 E. Gelenbe is with the Imperial College, London SW7 2AZ, UK.3 A. J. Alnsour is visiting faculty the University of Central Florida (on sabbatical leave from Al-Isra Private University, Amman, Jordan). A Sustainable Model for Integrating Current Topics in Machine Learning Research into the Undergraduate Curriculum2 serve as effective means to introduce undergraduate students to research [1].However, these interactions can reveal challenges with regards to sustaining undergraduate research over an extended period of time [2]. The Sustainable Model for Assimilating Research and Teaching (SMART) at UCF integrates current research into the undergraduate curriculum through a course sequence that has propagated beyond an NSF-funded Combined Research and Curriculum Development (CRCD) award [3], [4]. SMART reaches a wide audience of undergraduate students who may not otherwise have considered well-established research programs for undergraduates, such as the NSF-funded Research Experiences for Undergraduates (REUs). The effort describ...

show abstract

Section: B Ctml II Course Assessment and Evaluationmentioning

confidence: 99%

A Sustainable Model for Integrating Current Topics in Machine Learning Research Into the Undergraduate Curriculum

et al. 2009

Self Cite

View full text Add to dashboard Cite

show abstract

“…This indicates that increasing category number does not always bring performance improvements; too many categories may decline the testing performance (i.e. the problem of category proliferation [57,58]). The performance superiority of SSBA over BA reveals that SSBA can effectively exploit the useful information of unlabeled samples.…”

Section: Experiments With Benchmark Data Setsmentioning

confidence: 99%

Semi-supervised Bayesian ARTMAP

Tang

Han

2009

Appl Intell

View full text Add to dashboard Cite

This paper proposes a semi-supervised Bayesian ARTMAP (SSBA) which integrates the advantages of both Bayesian ARTMAP (BA) and Expectation Maximization (EM) algorithm. SSBA adopts the training framework of BA, which makes SSBA adaptively generate categories to represent the distribution of both labeled and unlabeled training samples without any user's intervention. In addition, SSBA employs EM algorithm to adjust its parameters, which realizes the soft assignment of training samples to categories instead of the hard assignment such as winner takes all. Experimental results on benchmark and real world data sets indicate that the proposed SSBA achieves significantly improved performance compared with BA and EM-based semi-supervised learning method; SSBA is appropriate for semi-supervised classification tasks with large amount of unlabeled samples or with strict demands for classification accuracy.

show abstract

“…In particular, from the students that presented their projects in the CRCD Symposium (see Section 5 for a list of CRCD projects at the symposium), the student of Project CRCD-A is currently pursuing his Masters in the Computer Engineering Department at the University of Central Florida, the student of Project CRCD-B is currently working at a nearby to UCF industry, the student of Project The work of Project CRCD-A was published in a conference venue 8 . The work of Project CRCD-B was published in a conference venue 12 , is under review in another conference venue 13 and is also under review in a journal venue 13 . The work of Project CRCD-C was published in a conference venue 3 , was also published in a journal venue 4 , and is currently under review in another journal venue 5 .…”

Section: Crcd Preliminariesmentioning

confidence: 99%

“…The work of Project CRCD-C was published in a conference venue 3 , was also published in a journal venue 4 , and is currently under review in another journal venue 5 . The work in Project CRCD-D was published in a conference venue (winning best paper award), and is under review in another conference venue 15 and in a journal venue 13 . The work in Project CRCD-E was published in two conference venues 10,11 .…”

Section: Crcd Preliminariesmentioning

confidence: 99%

Assessing And Evaluating Our Crcd Experiences At The University Of Central Florida: An Nsf Project

Georgiopoulos¹,

Gelenbe²,

DeMara³

et al.

2006 Annual Conference &Amp; Exposition Proceedings

Self Cite

View full text Add to dashboard Cite

Florida. He has been a reviewer for National Science Foundation, Journal of Parallel and Distributed Computing, IEEE Transactions on Parallel and Distributed Computing. His interests lie in the areas of Parallel and distributed processing, self-timed architectures. Avelino Gonzalez, University of Central Florida AVELINO GONZALEZ is a Professor of the School of Electrical Engineering and Computer Science at the University of Central Florida. He has co-authored a book entitled, "The Engineering of Knowledge-Based Systems: Theory and Practice". His research interests lie in the areas of artificial intelligence, context based behavior and representation, temporal reasoning, intelligent diagnostics and expert systems. Marcella Kysilka, University of Central Florida MARCELLA KYSILKA is a Professor and Assistant Chair of the Education Foundations Department at the University of Central Florida. She is active in her professional organizations and currently serves as Associate Editor of the "Journal of Curriculum and Supervision" (the scholarly journal of the Association for Supervision and Curriculum Development). Her research interests are in curriculum studies. Mansooreh Mollaghasemi, University of Central Florida MANSOOREH MOLLAGHASEMI is an Associate Professor at the Industrial Engineering and Management Sciences (IEMS) Department at the University of Central Florida. She has co-authored three books in the area of Multiple Objective Decision Making. Her research interests lie in Simulation Modeling and Analysis, Optimization, Multiple Criteria Decision Making, Neural Networks and Scheduling.

show abstract

Experiments with Safe μARTMAP : Effect of the network parameters on the network performance

Cited by 8 publications

References 16 publications

A Sustainable Model for Integrating Current Topics in Machine Learning Research Into the Undergraduate Curriculum

A Sustainable Model for Integrating Current Topics in Machine Learning Research Into the Undergraduate Curriculum

Semi-supervised Bayesian ARTMAP

Assessing And Evaluating Our Crcd Experiences At The University Of Central Florida: An Nsf Project

Contact Info

Product

Resources

About