Method home for mlp-mc-4

The mlp-mc-4 method uses a multilayer perceptron with one hidden layer and NO direct input-output connections, trained by a Bayesian method implemented using Markov chain Monte Carlo. The Automatic Relevance Determination scheme is NOT used for determining the relevance of the various inputs. The method can be used for both regression and classification. Aside from the negatives emphasized above, it is the same as mlp-mc-2. 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-mc-4 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.
Last Updated 20 May 1998
Comments and questions to: delve@cs.toronto.edu
Copyright