ORCID Profile
0000-0002-1931-585X
Current Organisations
University of Arizona
,
University of Michigan
,
Pennsylvania State University
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2021
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 11-1997
DOI: 10.1109/72.641472
Abstract: The performance of neural network simulations is often reported in terms of the mean and standard deviation of a number of simulations performed with different starting conditions. However, in many cases, the distribution of the in idual results does not approximate a Gaussian distribution, may not be symmetric, and may be multimodal. We present the distribution of results for practical problems and show that assuming Gaussian distributions can significantly affect the interpretation of results, especially those of comparison studies. For a controlled task which we consider, we find that the distribution of performance is skewed toward better performance for smoother target functions and skewed toward worse performance for more complex target functions. We propose new guidelines for reporting performance which provide more information about the actual distribution.
Publisher: Springer Berlin Heidelberg
Date: 2012
Publisher: IEEE
Date: 12-2011
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 1997
DOI: 10.1109/72.554195
Abstract: We present a hybrid neural-network for human face recognition which compares favourably with other methods. The system combines local image s ling, a self-organizing map (SOM) neural network, and a convolutional neural network. The SOM provides a quantization of the image s les into a topological space where inputs that are nearby in the original space are also nearby in the output space, thereby providing dimensionality reduction and invariance to minor changes in the image s le, and the convolutional neural network provides partial invariance to translation, rotation, scale, and deformation. The convolutional network extracts successively larger features in a hierarchical set of layers. We present results using the Karhunen-Loeve transform in place of the SOM, and a multilayer perceptron (MLP) in place of the convolutional network for comparison. We use a database of 400 images of 40 in iduals which contains quite a high degree of variability in expression, pose, and facial details. We analyze the computational complexity and discuss how new classes could be added to the trained recognizer.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 1999
DOI: 10.1109/78.782226
No related grants have been discovered for C Lee Giles.