A professor in the School of IT & Computing, Dr. Augustine Nsang, was the presenter at the SITC Seminar held on October 24.
The topic was “Dimensionality Reduction and Its Applications in Machine Learning.”
At the start of the presentation, the professor explained dimensionality reduction as an operation where a data set D containing n data points in high-dimensional Euclidean space is projected into a lower dimensional Euclidean space without suffering great distortion.
Dr. Nsang discussed various reasons for such reduction operations and went on to discuss the two categories of dimensionality reduction techniques.
“The first category includes those in which each attribute in the reduced set is a linear combination of the attributes in the original dataset and the second one in which the set of attributes in the reduced set is a proper subset of the attributes in the original dataset.”
He also discussed how dimensionality reduction can be applied in the reduction of text and image data and in the domains of clustering and classification, which are machine learning techniques.
The seminar is the third in the theme on artificial intelligence. On how the topic relates to the AI theme, he said by reducing the dimensionality of the data, it facilitates its processing.
“There are many machine learning algorithms… The larger the data, the slower the algorithm will run.”
He explained that often dimension of data is being reduced to facilitate processing, and it is different from compression, which changes the file size.
The presentation attracted members from across the university community.
Dr. Augustine Nsang earned his PhD in Computer Science from the University of Cincinnati, Ohio State, U.S. He holds a BSc in Joint Honors Computer Science/Mathematics from the University of Keele (Great Britain), and an MSc in Foundations of Artificial Intelligence from the University of Bristol (Great Britain).
Dr. Nsang has taught as an Assistant Lecturer of Computer Science at the University of Buea (Cameroon) for eight years (1993-2001) and has worked at the University of Cincinnati as a teaching/research assistant and as a math tutor for four years while pursuing his doctoral degree.
He has been teaching at AUN since September 2011. His research interests include dimensionality reduction and artificial intelligence/machine learning.
By Omorogbe Omorogiuwa