A unified framework for connectionist systems (Q1117857)
From MaRDI portal
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | A unified framework for connectionist systems |
scientific article |
Statements
A unified framework for connectionist systems (English)
0 references
1988
0 references
The paper proposes to treat connectionist systems (neural network models) within MAP (maximum a posteriori) estimation framework. The fundamental theorem assigns to every additive dynamical system summarizing function (specifying activity levels of visible neurons X for a given set of connection strengths) the subjective probability function representing the network's belief that X occurs in its environment. Classification and learning processes are then considered and evaluated from this viewpoint for the most popular neural networks paradigms [back-propagation; \textit{M. A. Cohen} and \textit{S. Grossberg} network, IEEE Trans. Syst. Man Cybern. 13, 815-826 (1983; Zbl 0553.92009); Hopfield model].
0 references
maximum likelihood estimation
0 references
MAP estimation
0 references
connectionist systems
0 references
neural network models
0 references
maximum a posteriori
0 references
additive dynamical system summarizing function
0 references
subjective probability function
0 references
Classification
0 references
learning processes
0 references
back-propagation
0 references
\textit{M. A. Cohen} and \textit{S. Grossberg} network
0 references
Hopfield model
0 references
