
PreviousNext
It has been known for quite a while that the Vapnik-Chervonenkis dimension
(VC-dimension) of a feedforward neural net with linear threshold gates is at
most O(w log w), where w is the total number of weights in the neural net.
We show in this paper that this bound is in ...
more >>>
We consider the fault diagnosis problem: how to use parallel testing
rounds to identify which processors in a set are faulty. We prove
that 4 rounds suffice when 3% or less of the processors are faulty,
and 4 rounds are necessary when any nontrivial constant fraction of
the processors are ...
more >>>
We introduce the notion of {\em natural} proof.
We argue that the known proofs of lower bounds on the complexity of explicit
Boolean functions in non-monotone models
fall within our definition of natural.
We show based on a hardness assumption
that natural proofs can't prove superpolynomial lower bounds ...
more >>>
PreviousNext