Name
Title | ||
|---|---|---|
Universal Approximation of Markov Kernels by Shallow Stochastic Feedforward Networks. |
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. |
Year | Venue | Field |
|---|---|---|
2015 | CoRR | Mathematical optimization,Markov chain,Artificial intelligence,Probabilistic logic,Machine learning,Mathematics,Binary number,Feed forward,Hidden semi-Markov model,Sigmoid function |
DocType | Volume | Citations |
Journal | abs/1503.07211 | 0 |
PageRank | References | Authors |
0.34 | 9 | 1 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Guido Montufar | 1 | 7 | 5.63 |