I don’t understand what you mean by the claim “the challenge is just as wrong”. Of course I’m aware of the NFL theorem. I’m also aware that data from the real world has structure that can be exploited to achieve better results than the NFL theorem seems to permit; if this weren’t true, the field of machine learning would be pointless. My claim is that the belief networks framework doesn’t really match that real world structure in most cases (but I’m ready to be proved wrong and in fact that’s my motivation for making the challenge).
I don’t understand what you mean by the claim “the challenge is just as wrong”. Of course I’m aware of the NFL theorem. I’m also aware that data from the real world has structure that can be exploited to achieve better results than the NFL theorem seems to permit; if this weren’t true, the field of machine learning would be pointless. My claim is that the belief networks framework doesn’t really match that real world structure in most cases (but I’m ready to be proved wrong and in fact that’s my motivation for making the challenge).