Nonlinear Independent Component Analysis

Hyvärinen, A., & Pajunen, P. (1999). Nonlinear Independent Component Analysis: Existence and Uniqueness Results. Neural Networks, 12(3), 429-439.

Type

Journal article

Intellectual base

Primary research

Year

1999

Volume

12

Issue

3

Pages

429-439

ISSN

0893-6080

DOI

10.1016/s0893-6080(98)00140-3

DOI registrant

Elsevier

Link

https://doi.org/10.1016/S0893-6080(98)00140-3

Cited from

statistics_experimental_design

Cited by

1 citation across 1 artifact.

Each citation links to the sentence it supports in the citing article.

Primes

• Identifiability
  • In machine learning, identifiability of factors in nonlinear ICA and of representations under disentanglement is exactly this prime at scale.

    This sourceEstablishes the non-identifiability of nonlinear ICA without further constraints — the identifiability question for latent factors and disentangled representations.

Verification

Does it exist? Confirmed. This work's DOI resolves to a registered record, which fixes its identity. That is all it fixes.

Does it back the claim? Not recorded. The single citation of this work carries no recorded support check.

Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.

See how references were verified.

Registry ID ref:128e2858981a · see in the full table