pith. sign in

arxiv: 1503.07211 · v1 · pith:4HMFEV4Mnew · submitted 2015-03-24 · 💻 cs.LG · stat.ML

Universal Approximation of Markov Kernels by Shallow Stochastic Feedforward Networks

classification 💻 cs.LG stat.ML
keywords unitshiddenfeedforwardkernelsmarkovnetworkstatesstochastic
0
0 comments X
read the original abstract

We establish upper bounds for the minimal number of hidden units for which a binary stochastic feedforward network with sigmoid activation probabilities and a single hidden layer is a universal approximator of Markov kernels. We show that each possible probabilistic assignment of the states of $n$ output units, given the states of $k\geq1$ input units, can be approximated arbitrarily well by a network with $2^{k-1}(2^{n-1}-1)$ hidden units.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.