Refines Cover's dichotomy counts and separation capacity for low-dimensional data by adjusting the general position assumption.
Bounds on the learning capacity of some multi-layer net- works,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
stat.ML 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Extends Cover's separation capacity to scattering networks by counting realizable dichotomies and identifies governing factors in network building blocks.
citing papers explorer
-
Function-Counting Theory for Low-Dimensional Data Structures
Refines Cover's dichotomy counts and separation capacity for low-dimensional data by adjusting the general position assumption.
-
Separation Capacity of Scattering Networks
Extends Cover's separation capacity to scattering networks by counting realizable dichotomies and identifies governing factors in network building blocks.