No label defined (Q3973618)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 16927
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | No label defined |
scientific article; zbMATH DE number 16927 |
Statements
26 June 1992
0 references
Gibbs distribution
0 references
Markov chain
0 references
binary-state neural network
0 references
Boltzmann machine
0 references
Hopfield net
0 references
0.8118553161621094
0 references
0.7932109236717224
0 references
0.786284863948822
0 references
[For the entire collection see Zbl 0724.00018.] A Boltzmann machine is a binary-state neural network whose states form a stationary Markov chain with an equilibrium Gibbs distribution. \textit{Alspector} and \textit{Allen} [Advanced research in VLSI, in: Proc. 1987 Stanford Conference, MIT press, Cambridge, 313-349)] proposed to approximate a Boltzmann machine by injecting noise in a Hopfield net. The main result of this paper shows that an exact construction of Boltzmann machine can be achieved by injecting noise in a Hopfield net.
0 references
