Weizmann Logo
ECCC
Electronic Colloquium on Computational Complexity

Under the auspices of the Computational Complexity Foundation (CCF)

Login | Register | Classic Style



LATEST > REPORTS:
RSS-Feedprevious PreviousNext next

TR99-005 | 21st December 1998
Michael Schmitt

On the Sample Complexity for Nonoverlapping Neural Networks

A neural network is said to be nonoverlapping if there is at most one
edge outgoing from each node. We investigate the number of examples
that a learning algorithm needs when using nonoverlapping neural
networks as hypotheses. We derive bounds for this sample complexity
in terms of the Vapnik-Chervonenkis dimension. ... more >>>


TR99-004 | 3rd February 1999
Valentine Kabanets

Almost $k$-Wise Independence and Boolean Functions Hard for Read-Once Branching Programs

Revisions: 1

Andreev et al.~\cite{ABCR97} give constructions of Boolean
functions (computable by polynomial-size circuits) that require large
read-once branching program (1-b.p.'s): a function in P that requires
1-b.p. of size at least $2^{n-\polylog(n)}$, a function in quasipolynomial
time that requires 1-b.p. of size at least $2^{n-O(\log n)}$, and a
function in LINSPACE ... more >>>


TR99-003 | 18th December 1998
Stephen A. Fenner, Frederic Green, Steven Homer, Randall Pruim

Determining Acceptance Possibility for a Quantum Computation is Hard for the Polynomial Hierarchy

It is shown that determining whether a quantum computation
has a non-zero probability of accepting is at least as hard as the
polynomial time hierarchy. This hardness result also applies to
determining in general whether a given quantum basis state appears
with nonzero amplitude in a superposition, or whether a ... more >>>



previous PreviousNext next


ISSN 1433-8092 | Imprint