Pith. sign in

REVIEW 6 cited by

A Survey on Universal Approximation Theorems

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2407.12895 v1 pith:D2ZMRA6R submitted 2024-07-17 cs.LG cs.SYeess.SY

Midhun T Augustine This is my paper · ORCID
classification cs.LGcs.SYeess.SY
keywords approximationtheoremtheoremsuatsuniversalarbitraryarnoldaspects
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

This paper discusses various theorems on the approximation capabilities of neural networks (NNs), which are known as universal approximation theorems (UATs). The paper gives a systematic overview of UATs starting from the preliminary results on function approximation, such as Taylor's theorem, Fourier's theorem, Weierstrass approximation theorem, Kolmogorov - Arnold representation theorem, etc. Theoretical and numerical aspects of UATs are covered from both arbitrary width and depth.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Hybrid Least Squares/Gradient Descent Methods for DeepONets

    cs.LG 2025-08 conditional novelty 6.0 of 10

    A hybrid LS/GD training scheme for DeepONets, using a factored least-squares solve for the last layer, converges in far fewer work units than Adam-only training on advection, diffusion-reaction, and Poisson benchmarks.

  2. Hybrid Least Squares/Gradient Descent Methods for MIONets

    cs.LG 2026-07 conditional novelty 5.0 of 10

    A hybrid least squares / gradient descent method accelerates MIONet training by exploiting multilinear structure in last-layer branch parameters via alternating least squares with Kronecker/Khatri-Rao factorization.

  3. SGS-GNN: A Supervised Graph Sparsification method for Graph Neural Networks

    cs.LG 2025-02 conditional novelty 5.0 of 10

    A supervised edge-sampling sparsifier that keeps only 20% of edges can match or beat the full graph for GNN node classification, with especially large gains on heterophilic graphs.

  4. Assessing the Advantages and Limitations of Quantum Neural Networks in Regression Tasks

    quant-ph 2025-08 conditional novelty 4.0 of 10

    Quantum neural networks strongly outperform narrow classical networks on smooth function regression, but the advantage depends on comparison design and disappears on discontinuous functions.

  5. Ethics through the Facets of Artificial Intelligence

    cs.CY 2025-07 conditional novelty 4.0 of 10

    The author introduces three facets of AI (scientific, technological, sociotechnical imaginary) and a three-layer responsibility framework for ethical assessment, without providing an executable specification.

  6. A Study of Hybrid and Evolutionary Metaheuristics for Single Hidden Layer Feedforward Neural Network Architecture

    cs.NE 2025-06 reject novelty 2.0 of 10

    A hybrid PSO-SGD optimizer is tested on small feedforward networks, with the paper claiming large MSE reductions that the presented tables only partially support.

Pith tools