Method home for mlp-ese-1

This learning method trains ensembles of multilayer perceptrons using early stopping. The networks all have identical architecture: fully connected with a single hidden layer of hyperbolic tangent units and linear output units. The minimisation algorithm is based on conjugate gradients. Both hypertext (generated by LaTeX2HTML) and postscript descriptions of the algorithm are available. A detailed description of the minimization procedure is available in postscript.


The source code for a C implementation (including the documentation) is available as a compressed tar file.


Directory listing of the results available for the mlp-ese-1 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

Last Updated by Carl Edward Rasmussen, September 27, 1996