|
|
 |
|
IEEE
Computational Intelligence Society
Ottawa
Chapter
|
|
|
|
Next Meetings/Events
The seminar will also be available as a webinar (space is limited).
Date |
Wednesday May 12, 2010 |
Time |
19:00-20:00 |
Location |
Room 5077, SITE Building, University of Ottawa |
Title |
The Use of General Neuron Functions within Neural Networks |
Speaker |
Alan J. Barton |
| |
NRC-CNRC Institute for Information Technology |
| |
|
Abstract
Classical Artificial Neural Networks (ANNs) may have their neurons organized in many ways. For example, Feedforward Neural Networks are aggregations of weights multiplied by inputs and controlled via activation functions; with the potential addition of bias nodes.
This presentation will demonstrate the use of a methodology for construction of ANNs that do not require the use of weights nor the apriori specification of activation functions when learning the functions associated to the neurons within the ANN as is performed within the classical case. A brief discussion of related work and examples will be shown from various applications of the approach, including:
- Biological Data, such as Magnetic Resonance Spectra from Brain Cancer samples and clinical data from Breast Cancer samples,
- Geophysical Prospecting Data, such as from Insunza measurements for learning about the presence of an underground cave, and
- Hydrochemical Data, such as from Werenskiold glacial water samples for learning about global climate changes.
In addition, if time permits, a preliminary analysis of the parameters controlling the construction of the ANNs will be stated (e.g. the Parameter Space) along with a discussion of one possible way to analyse the set of constructed ANNs (e.g. the Mathematical Expression Space; based on a recently published similarity measure).
|
| |
Speaker Bio
Alan J. Barton's current research interests lie within Computational Intelligence (e.g. Neural Networks, Evolutionary Computation, etc.) and High Performance Computing (e.g. Distributed and Parallel Computation, etc.). He holds a Master of Computer Science (M.C.S.) from Carleton University in Ottawa, Ontario, Canada (2009) and has a combined Computer Science and Mathematics degree (B.Sc.) from the University of Victoria in British Columbia, Canada (2000). He has also completed the required course and laboratory work (Proteomics, Genomics and Bioinformatics) and obtained a certificate in BioInformatics (2006).
|
|
