The problem with #machinelearning in a nutshell, via extensional vs intensional logic:
A: {2, 4, 6, 8, 10, ... X}
B: {2x: x ∈ N}
There is no way for a statistical, asymbolic machine to arrive at B from A, no matter how large you choose X @GaryMarcus @filippie509 #ai
-
I think this example was solved in inductive programming two decades ago. For example http://kdde.di.uniba.it/publications/malerba.publications/FI_atre.pdf … and many other papers that learn odd/even concepts. There's plenty of symbolic machine learning going on, also today.
indeed i have an example, re Auofill, in my medium post “in defense of skepticism”
