geocomputation, computational aspects, neurocomputing

AM-66 - Multi-layer feed-forward neural networks
  • Analyze the stability of the network using multiple runs with the same training data and architecture
  • Compare and contrast classification results when the architecture of the network and initial parameters are changed
  • Differentiate between feed-forward and recurrent architectures
  • Describe the architecture and components of a feed-forward neural network
AM-67 - Space-scale algorithms
  • Describe how space-scale algorithms can, or should, be used
AM-65 - Geospatial data classification
  • Compare and contrast the assumptions and performance of parametric and non-parametric approaches to multivariate data classification
  • Describe three algorithms that are commonly used to conduct geospatial data classification
  • Explain the effect of including geospatial contiguity as an explicit neighborhood classification criterion
  • Compare and contrast the results of the neural approach to those obtained using more traditional Gaussian maximum likelihood classification (available in most remote sensing systems)
AM-63 - Non-linearity relationships and non-Gaussian distributions
  • Understand how some machine learning methods might be more adept at modeling or representing such distributions
  • Define non-linear and non-Gaussian distributions in a geospatial data environment
  • Exemplify non-linear and non-Gaussian distributions in a geospatial data environment
AM-65 - Geospatial data classification
  • Compare and contrast the assumptions and performance of parametric and non-parametric approaches to multivariate data classification
  • Describe three algorithms that are commonly used to conduct geospatial data classification
  • Explain the effect of including geospatial contiguity as an explicit neighborhood classification criterion
  • Compare and contrast the results of the neural approach to those obtained using more traditional Gaussian maximum likelihood classification (available in most remote sensing systems)
AM-67 - Space-scale algorithms
  • Describe how space-scale algorithms can, or should, be used
AM-63 - Non-linearity relationships and non-Gaussian distributions
  • Understand how some machine learning methods might be more adept at modeling or representing such distributions
  • Define non-linear and non-Gaussian distributions in a geospatial data environment
  • Exemplify non-linear and non-Gaussian distributions in a geospatial data environment
AM-68 - Rule learning
  • Describe how a neural network may use training rules to learn from input data
AM-67 - Space-scale algorithms
  • Describe how space-scale algorithms can, or should, be used
AM-65 - Geospatial data classification
  • Compare and contrast the assumptions and performance of parametric and non-parametric approaches to multivariate data classification
  • Describe three algorithms that are commonly used to conduct geospatial data classification
  • Explain the effect of including geospatial contiguity as an explicit neighborhood classification criterion
  • Compare and contrast the results of the neural approach to those obtained using more traditional Gaussian maximum likelihood classification (available in most remote sensing systems)

Pages