On the public citation graph

The computational intractability of training sigmoidal neural networks

0 signed · 45 inferred · view as graph

Inferred edges come from two machine sources: sweeps of open repository metadata (mostly SSRN and Zenodo), and a bulk OpenAlex citation snapshot. Every row below is labelled with the one it came from. Neither is a complete citation index — absence here is not evidence of absence.

Is this your work? Sign in with ORCID and put your name on the claims that are yours.
Claim with ORCID
Reference health. See whether every reference in this work resolves to a known work and none has been retracted — and get a dated CiteStamped badge you can embed.
See reference health

What this work says

Outgoing claims: the papers this work cites, builds on, or argues with.

inferredcites →https://doi.org/10.1016/0020-0190(93)90064-gopenalex-snapshot
Computational limitations on training sigmoid neural networks
inferredcites →https://doi.org/10.1016/0022-0000(92)90039-lopenalex-snapshot
Feedforward nets for interpolation and classification
inferredcites →https://doi.org/10.1016/0041-5553(80)90061-0openalex-snapshot
Polynomial algorithms in linear programming
inferredcites →https://doi.org/10.1016/0304-3975(78)90006-3openalex-snapshot
The densest hemisphere problem
inferredcites →https://doi.org/10.1016/s0893-6080(05)80010-3openalex-snapshot
Training a 3-node neural network is NP-complete
inferredcites →https://doi.org/10.1109/18.256500openalex-snapshot
Universal approximation bounds for superpositions of a sigmoidal function
inferredcites →https://doi.org/10.1109/18.312166openalex-snapshot
Good weights and hyperbolic kernels for neural networks, projection pursuit, and pattern classification: Fourier strategies for extracting information from high-dimensional data
inferredcites →https://doi.org/10.1109/5.58342openalex-snapshot
Constructive approximations for neural networks by sigmoidal functions
inferredcites →https://doi.org/10.1145/180139.181009openalex-snapshot
On a learnability question associated to neural networks with continuous activations (extended abstract)
inferredcites →https://doi.org/10.1214/aos/1176348546openalex-snapshot
A Simple Lemma on Greedy Approximation in Hilbert Space and Convergence Rates for Projection Pursuit Regression and Neural Network Training
inferredcites →https://doi.org/10.7551/mitpress/4932.001.0001openalex-snapshot
Neural Network Design and the Complexity of Learning

What points at this work

Incoming claims: where this work appears in other papers’ reference lists and arguments.

inferred← citeshttps://doi.org/10.2139/ssrn.7070962openalex-extracted
inferred← citeshttps://doi.org/10.1007/3-540-40992-0_20openalex-snapshot
On Approximate Learning by Multi-layered Feedforward Circuits
inferred← citeshttps://doi.org/10.1007/3-540-45583-3_9openalex-snapshot
Minimizing the Quadratic Training Error of a Sigmoid Neuron Is Hard
inferred← citeshttps://doi.org/10.1007/3-540-49097-3_5openalex-snapshot
Hardness Results for Neural Network Approximation Problems
inferred← citeshttps://doi.org/10.1007/978-1-4471-0807-8_9openalex-snapshot
Efficient neural network learning
inferred← citeshttps://doi.org/10.1007/978-3-030-81716-9_18openalex-snapshot
Interpretable Machine Learning for Function Approximation in Structural Health Monitoring
inferred← citeshttps://doi.org/10.1007/s00041-004-8003-5openalex-snapshot
Nonlinear Approximation with Dictionaries I. Direct Estimates
inferred← citeshttps://doi.org/10.1007/s00365-003-0532-7openalex-snapshot
On Approximation with Spline Generated Framelets
inferred← citeshttps://doi.org/10.1016/j.tcs.2005.09.008openalex-snapshot
On approximate learning by multi-layered feedforward circuits
inferred← citeshttps://doi.org/10.1016/s0304-3975(01)00057-3openalex-snapshot
Hardness results for neural network approximation problems
inferred← citeshttps://doi.org/10.1016/s0893-6080(00)00055-1openalex-snapshot
Modular neural networks for non-linearity recovering by the Haar approximation
inferred← citeshttps://doi.org/10.1016/s0925-2312(03)00369-2openalex-snapshot
Meta learning evolutionary artificial neural networks
inferred← citeshttps://doi.org/10.1016/s1474-6670(17)34967-4openalex-snapshot
Prediction Algorithms: Complexity, Concentration and Convexity
inferred← citeshttps://doi.org/10.1016/s1574-0706(05)01009-8openalex-snapshot
Chapter 9 Approximate Nonlinear Forecasting Methods
inferred← citeshttps://doi.org/10.1017/s0962492900002919openalex-snapshot
Approximation theory of the MLP model in neural networks
inferred← citeshttps://doi.org/10.1023/a:1007577530334openalex-snapshot
Prequential and Cross-Validated Regression Estimation
inferred← citeshttps://doi.org/10.1080/01621459.2000.10474249openalex-snapshot
Book Reviews
inferred← citeshttps://doi.org/10.1109/18.650998openalex-snapshot
Memory-universal prediction of stationary random processes
inferred← citeshttps://doi.org/10.1109/18.737520openalex-snapshot
On the infeasibility of training neural networks with small mean-squared error
inferred← citeshttps://doi.org/10.1109/cdc.2006.377696openalex-snapshot
A continuous-time global adaptive observer of the parameters of a SISO sigmoidal neural network
inferred← citeshttps://doi.org/10.1109/ijcnn.2011.6033546openalex-snapshot
Toward constructive methods for sigmoidal neural networks - function approximation in engineering mechanics applications
inferred← citeshttps://doi.org/10.1111/mafi.12125openalex-snapshot
CONVERGENCE OF A LEAST‐SQUARES MONTE CARLO ALGORITHM FOR AMERICAN OPTION PRICING WITH DEPENDENT SAMPLE DATA
inferred← citeshttps://doi.org/10.1134/s0081543818040120openalex-snapshot
Some Problems in the Theory of Ridge Functions
inferred← citeshttps://doi.org/10.1142/s0218213098000172openalex-snapshot
A CONSTRUCTIVE NEURAL NETWORK ALGORITHM FOR FUNCTION APPROXIMATION USING LOCALLY FIT SIGMOIDS
inferred← citeshttps://doi.org/10.1162/089976602760408035openalex-snapshot
Training a Single Sigmoidal Neuron Is Hard
inferred← citeshttps://doi.org/10.1162/089976699300016449openalex-snapshot
Training a Sigmoidal Node Is Hard
inferred← citeshttps://doi.org/10.1214/aos/1015957398openalex-snapshot
Local greedy approximation for nonlinear regression and neural network training
inferred← citeshttps://doi.org/10.1214/aos/1065705119openalex-snapshot
Ridgelets: estimating with ridge functions
inferred← citeshttps://doi.org/10.1609/aaai.v38i11.29118openalex-snapshot
Complexity of Neural Network Training and ETR: Extensions with Effectively Continuous Functions
inferred← citeshttps://doi.org/10.2139/ssrn.5022673openalex-snapshot
Non-Integrability of Gradient Flow in Two-Layer Networks and the Absence of Closed-Form Descriptions
inferred← citeshttps://doi.org/10.24963/ijcai.2023/409openalex-snapshot
Cardinality-Minimal Explanations for Monotonic Neural Networks
inferred← citeshttps://doi.org/10.3390/aerospace12050412openalex-snapshot
Validation of a Machine Learning Model for Certification Using Symbolic Regression and a Behaviour Envelope
inferred← citeshttps://doi.org/10.3390/make3020018openalex-snapshot
Estimating Neural Network’s Performance with Bootstrap: A Tutorial
inferred← citeshttps://doi.org/10.48550/arxiv.2102.09798openalex-snapshot
Training Neural Networks is ER-complete
Editorial review for independent work. ICSAC — the Institute for Complexity Science and Advanced Computing — runs a structured editorial panel for researchers publishing outside journals, and publishes on CiteStamp rails. Submission is free and goes through ORCID: icsacinstitute.org/submit.