The mlp-bgd-2 method does regression and classification using a
multilayer perceptron neural network with one hidden layer, trained by
batch gradient descent, with learning rates out of inputs dynamically
adjusted based on the fourth power of the gradient. Aside from this
adjustment, it operates the same as mlp-bgd-1.
See the notes for more details.
Software
This method uses the software for flexible Bayesian modeling written
by Radford Neal (release of 1997-06-22), available from
Radford Neal's home page.
Results
Directory listing of the results (and source
files) available for the mlp-bgd-2 method. Put the desired files
in the appropriate methods directory in your delve hierarchy and
uncompress them with using the "gunzip *.gz" command and
untar them using "tar -xvf *.tar".
Related References
Neal, R. M. (1998) ``Assessing relevance determination methods using DELVE'',
to appear in C. M. Bishop (ed) Generalization in Neural Networks and
Machine Learning, Springer-Verlag.