Dave Harris wrote: > Mitchell Timin wrote: > >> Working with short paths and small neuron counts is a lot nicer because >> everything moves very quickly. Runmany.bat only takes a few minutes. >> Since I'm mainly interested in ANNs that do 100%, I think it's best that >> we work our way upward from the bottom. Hence I would like to find the >> ANN with the fewest neurons that can do 100% on the 3-step path. >> >> I you would like to help in this search, please do. At the moment I >> won't tell you exactly how to proceed, except that in your waybak.ini >> file, neurons should be 6 or less, minSteps should be 3, and maxSteps >> could be 3, 4 or 5. Other than that, I'm not sure what would be most >> fruitful. My advice is, play around with the problem. >> >> > > Using minSteps = 3, maxSteps = 3, and neurons = 4, I consistently 'top out' > at a fitness of .8743 > It's likely that 4 neurons can't perform this task, but it's also possible that it is extremely unlikely to evolve to it, even if it is possible. 3 neurons can hold the data of a 3 step path, but additional scratchpad RAM is required, I'm pretty sure. Just as if you wrote a program to remember 3 bits and then play them back, you would need some RAM for stack or variables, in addition to what's required to remember the 3 bits. Can you write an assembler program that does this without any additional RAM nor registers? If so, then a 3 neuron ANN might do the job.
Maybe 5 neurons can do it. m -- I'm proud of http://ANNEvolve.sourceforge.net. If you want to write software, or articles, or do testing or research for ANNEvolve, let me know. ------------------------------------------------------------------------- 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
