For those who like pure math in their AI safety: a new paper claims that the decidability of “verification” of deep learning networks with smooth activation functions, is equivalent to the decidability of propositions about the real number field with exponentiation.
For those who like pure math in their AI safety: a new paper claims that the decidability of “verification” of deep learning networks with smooth activation functions, is equivalent to the decidability of propositions about the real number field with exponentiation.
The point is that the latter problem (“Tarski’s exponential function problem”) is well-known and unresolved, so there’s potential for crossover here.