In general, turning off ENF will fuck up learning... though in some cases it might not
what you want to do for biology is not turn off ENF for learning, but rather convert the ENF to DNF afterwards for analysis There are lots of existing code libraries for converting arbitrary Boolean expressions to DNF, e.g. https://github.com/bpodgursky/jbool_expressions or probably some R code somewhere... On Fri, Nov 17, 2017 at 6:08 PM, 'Nil Geisweiller' via opencog <[email protected]> wrote: > On 11/17/2017 04:19 PM, Michael Duncan wrote: >> >> thanks, nil! i might try to implement something for the URE. if ENF is >> disabled in MOSES, how would that affect performance? > > > It depends on the problem. > > The thing is, if DNF is enabled, then there is little learning required > because an optimal, though gigantic, DNF can be inferred from the data, then > learning consists of pruning this giant DNF to reach an adequate trade-off > between fitness of data and simplicity. > > Nil > >> >> On Fri, Nov 17, 2017 at 4:50 PM, Nil Geisweiller <[email protected] >> <mailto:[email protected]>> wrote: >> >> Hi Mike, >> >> I'm not aware of any code doing that on the AtomSpace's end. >> >> Yidnekachew Wondimu is developing a URE-base reduct engine may >> ultimately be able to do that sort of things, but it might take a >> while before it's ready. >> >> Alternatively, I think there's a way you could tweak MOSES to output >> models in DNF, by disabling ENF reduction and enabling some >> experimental flags. I have forgotten the details of that but, if >> that seems worthwhile to you, I can dig that up. >> >> Nil >> >> On 11/17/2017 03:03 PM, Michael Duncan wrote: >> >> i want to convert moses models from elegant normal form to >> disjunctive normal form to get a set of conjunctions whose >> features can then be used for inference against background >> knowledge. >> for instance, if a model is converted to DNF and has the clause: >> >> (and geneV ~geneW geneX ~geneY ~geneZ) >> >> then maybe a pathway with geneV and geneX is active in the case >> vs the control phenotype, >> or a pathway with geneW, geneY, and geneZ is active the control >> vs case phenotype. >> >> -- You received this message because you are subscribed to >> the >> Google Groups "opencog" group. >> To unsubscribe from this group and stop receiving emails from >> it, send an email to [email protected] >> <mailto:opencog%[email protected]> >> <mailto:[email protected] >> <mailto:opencog%[email protected]>>. >> To post to this group, send email to [email protected] >> <mailto:[email protected]> >> <mailto:[email protected] >> <mailto:[email protected]>>. >> Visit this group at https://groups.google.com/group/opencog >> <https://groups.google.com/group/opencog>. >> To view this discussion on the web visit >> >> https://groups.google.com/d/msgid/opencog/98859455-c0df-40eb-9d34-1569a149bb4e%40googlegroups.com >> >> <https://groups.google.com/d/msgid/opencog/98859455-c0df-40eb-9d34-1569a149bb4e%40googlegroups.com> >> >> <https://groups.google.com/d/msgid/opencog/98859455-c0df-40eb-9d34-1569a149bb4e%40googlegroups.com?utm_medium=email&utm_source=footer >> >> <https://groups.google.com/d/msgid/opencog/98859455-c0df-40eb-9d34-1569a149bb4e%40googlegroups.com?utm_medium=email&utm_source=footer>>. >> For more options, visit https://groups.google.com/d/optout >> <https://groups.google.com/d/optout>. >> >> > > -- > You received this message because you are subscribed to the Google Groups > "opencog" group. > To unsubscribe from this group and stop receiving emails from it, send an > email to [email protected]. > To post to this group, send email to [email protected]. > Visit this group at https://groups.google.com/group/opencog. > To view this discussion on the web visit > https://groups.google.com/d/msgid/opencog/7000a3af-990a-5a87-aed3-57e47cf8b086%40gmail.com. > > For more options, visit https://groups.google.com/d/optout. -- Ben Goertzel, PhD http://goertzel.org "I am God! I am nothing, I'm play, I am freedom, I am life. I am the boundary, I am the peak." -- Alexander Scriabin -- You received this message because you are subscribed to the Google Groups "opencog" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To post to this group, send email to [email protected]. Visit this group at https://groups.google.com/group/opencog. To view this discussion on the web visit https://groups.google.com/d/msgid/opencog/CACYTDBeMdW70gLbe2CFSD4FAEnxsyV5NOCPnWN-UqNkdVf6Sdw%40mail.gmail.com. For more options, visit https://groups.google.com/d/optout.
