Abstract
No public abstract is available from the verified source records.
Liqun Ren
Abstract
Authors
Institutions
No ROR-resolved institution is linked to this work yet.
Provenance
crossref
Confidence 100%
unpaywall
Confidence 95%
datacite
Confidence 0%
No local reference links have been materialized yet.
No local citing links have been materialized yet.
Approximation by superpositions of a sigmoidal function
10.1007/bf02551274 · 1989
Multilayer feed-forward networks are universal approximators
10.1016/0893-6080(89)90020-8 · 1989
On the approximate realization of continuous mappings by neural networks
10.1016/0893-6080(89)90003-8 · 1989
Dynamic node creation in back-propagation network
10.1080/09540098908915647 · 1989
Some comments on Cp
10.2307/1267380 · 1973
Unresolved referenced work
1984
Cross validation choice and assessment of statistical predictions
10.1111/j.2517-6161.1974.tb00994.x · 1974
Unresolved referenced work
Kept as external metadata until matched
On the use of a linear model for the identification of feedback system
10.1007/bf02911655 · 1968
Fitting auto-regressive model for prediction
10.1007/bf02532251 · 1969
Network information criterion-determining the number of hidden units for an artificial neural network model
10.1109/72.329683 · 1994
A new look at the statistical model identification
1974
Statistical ideas for selecting network architectures
1995
Information theory as an extension of the maximum likelihood principle
1973
On the capabilities of multilayer perceptrons
10.1016/0885-064x(88)90020-9 · 1988
Bounds on number of hidden neurons in multilayer perceptrons
10.1109/72.80290 · 1991
A simple method to derive bounds on the size and to train multilayer neural networks
10.1109/72.88168 · 1991
Unresolved referenced work
1989
Unresolved referenced work
Kept as external metadata until matched
A learning algorithm for Boltzman machines
10.1207/s15516709cog0901_7 · 1985
Unresolved referenced work
1986
Genetic algorithm and neural networks: optimizing connections and connectivity
10.1016/0167-8191(90)90086-o · 1990
Evolving neural networks
1990
A new approach for finding the global minimum of error function of neural networks
10.1016/0893-6080(89)90021-x · 1989
Training neural nets through stochastic minimization
10.1016/0893-6080(94)90088-4 · 1994
Deterministic global optimal FNN training algorithms
10.1016/0893-6080(94)90024-8 · 1994
Towards faster stochastic gradient search
1992
Training feedforward networks with the Marquardt algorithm
10.1109/72.329697 · 1994
A mathematical description of the strength properties of concrete under generalized stress
10.1680/macr.1979.31.108.151 · 1979
Experimental investigation of multiaxial strength of concrete and analysis of the failure criteria
1996
No additional external references are available.