Mitchell Timin wrote: > >> Mitchell Timin wrote: > >> > >>> Biggerun.bat found a perfect 4-neuron ANN for the 3 step path; it is > >>> attached. It was evolved for 3 and 4 steps, hence the name. > >>> > But now the question is, can you illustrate that ANN with a python > program for VizANN-4? It would be helpful if some of the weights can be > eliminated, and that's prolly the case. A C program that can do that is > in the "extras" folder of the 4Play project. The program is called > examine.c. It finds weights that can be zeroed, and then produces an > equivalent chromosome with those zeroes. However, you would have to > modify examine.c to use our current fitness function rather than the one > from 4 play. If you want to do this I will help. >
I began work this morning on wbreduce (waybak reduce), similar to the 4Play examine program. The program tries to eliminate neurons, and failing that, attempts to eliminate one or more weights. This program only applies to perfect ANNs. There are some differences (for example, 20 sets of weights in the chromosome file, of which one (or more) is a perfect ANN.) I haven't encountered anything I don't understand yet. I should have something operational today or tomorrow. Dave ------------------------------------------------------------------------- Using Tomcat but need to do more? Need to support web services, security? Get stuff done quickly with pre-integrated technology to make your job easier Download IBM WebSphere Application Server v.1.0.1 based on Apache Geronimo http://sel.as-us.falkag.net/sel?cmd=lnk&kid=120709&bid=263057&dat=121642
