search for: backprop

...I would like to know which member variable is being accessed in the `load' statement but there appears to be no way to relate the %.omp_data_i to {!236}. I am using LLVM 3.1 with dragonegg 3.1. The file is being compiled with the following line: gcc -fplugin=dragonegg.so -flto -emit-llvm -g -S backprop.c -g -O2 -fopenmp -o backprop.o.bc Ashay -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20120903/eef37e57/attachment.html>

...rlo. ¿Alguien me puede ayudar? La red neural que creo la hago con el siguiente código: nnet.sintoma<-neuralnet(hipocatotal01~edad+pthyugulardchapre+pthyugulardchapost+tasa_derecha+pthyugularizqpre+pthyugularizqpost+tasa_izquierda+nºparatirmalaviabilidad,data=Datos.chelo,hidden=1,algorithm="backprop",learningrate=0.01, hidden=1,threshold = 0.01,act.fct="tanh",linear.output=FALSE) A partir de aquí puedo ver la red e incluso ver la imagen de la red con los diferentes pesos. Entonces, me gustaría poder obtener los valores predichos por la red para luego poder hacer la curva ROC...

...tors), and make sure SCCP is on par with the other two costant propagation passes we have in llvm (and maybe garbage collect them). Danny suggested an improvement could be that of propagating facts in both directions (GCC does that as a separate pass https://gcc.gnu.org/svn/gcc/trunk/gcc/gimple-ssa-backprop.c). I have no immediate plans to work on this (I suspect NewGVN and other places will keep me busy for a while), but I hope to eventually get there. #### Thanks Eli Friedman and Daniel Berlin provided very insightful conversations/suggestions on how to tackle the problems, and provided early feedb...

...is on par > with the other two costant propagation passes we have in llvm (and > maybe garbage collect them). > Danny suggested an improvement could be that of propagating facts in > both directions (GCC does that as a separate pass > https://gcc.gnu.org/svn/gcc/trunk/gcc/gimple-ssa-backprop.c). I have > no immediate plans to work on this (I suspect NewGVN and other places > will keep me busy for a while), but I hope to eventually get there. > > #### Thanks > Eli Friedman and Daniel Berlin provided very insightful > conversations/suggestions on how to tackle the probl...

...is on par > with the other two costant propagation passes we have in llvm (and > maybe garbage collect them). > Danny suggested an improvement could be that of propagating facts in > both directions (GCC does that as a separate pass > https://gcc.gnu.org/svn/gcc/trunk/gcc/gimple-ssa-backprop.c). I have > no immediate plans to work on this (I suspect NewGVN and other places > will keep me busy for a while), but I hope to eventually get there. > > #### Thanks > Eli Friedman and Daniel Berlin provided very insightful > conversations/suggestions on how to tackle the probl...

...the other two costant propagation passes we have in llvm (and > > maybe garbage collect them). > > Danny suggested an improvement could be that of propagating facts in > > both directions (GCC does that as a separate pass > > https://gcc.gnu.org/svn/gcc/trunk/gcc/gimple-ssa-backprop.c). I have > > no immediate plans to work on this (I suspect NewGVN and other places > > will keep me busy for a while), but I hope to eventually get there. > > > > #### Thanks > > Eli Friedman and Daniel Berlin provided very insightful > > conversations/suggesti...

...ostant propagation passes we have in llvm (and >> > maybe garbage collect them). >> > Danny suggested an improvement could be that of propagating facts in >> > both directions (GCC does that as a separate pass >> > https://gcc.gnu.org/svn/gcc/trunk/gcc/gimple-ssa-backprop.c). I have >> > no immediate plans to work on this (I suspect NewGVN and other places >> > will keep me busy for a while), but I hope to eventually get there. >> > >> > #### Thanks >> > Eli Friedman and Daniel Berlin provided very insightful >> &gt...