 Home

Codex Wiki

Mathematics

Area of mathematics

Foundations of mathematics

Statistical learning theory

Growth bound for signs of m-term linear combinations

A bias-free network with $p$ inputs, $m$ sign-activated hidden nodes, and a thresholded linear output satisfies
$$
s(\mathcal H,n)\leq(n+1)^{(p+1)m}.
$$
The hidden units contribute $s(\mathcal G,n)^m\leq(n+1)^{pm}$ sample patterns, and the output weights contribute $(n+1)^m$.


Growth bound for a single-hidden-layer sign network

Past exam of the mathematics course of the University of Cambridge / 2023 / ii / Paper 2 / 31J / e / Solution

Growth bound for a single-hidden-layer sign network

 Ancestors (6)

 Incoming links (1)

 Discussion (0)

 Articles by others on the same topic (0)

Growth bound for a single-hidden-layer sign network

 Ancestors (6)

 Incoming links (1)

 Discussion (0)  Subscribe (1)

 Articles by others on the same topic (0)

 Discussion (0)