On the Achievability of Blind Source Separation for High-Dimensional Nonlinear Source Mixtures

DOI10.1162/neco_a_01378zbMath1469.94031arXiv1808.00668OpenAlexW3152632243MaRDI QIDQ5004361

Takuya Isomura, Taro Toyoizumi

Publication date: 30 July 2021

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1808.00668

zbMATH Keywords

independent component analysisprincipal component analysisrecovering nonlinearly mixed sources

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Related Items (2)

Discussion of: ``Identifiability of latent-variable and structural-equation models: from linear to nonlinear ⋮ Blind Nonnegative Source Separation Using Biological Neural Networks

Uses Software

• darch
• NICE

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A simplified neuron model as a principal component analyzer
• Independent component analysis, a new concept?
• Multilayer feedforward networks are universal approximators
• Principal component analysis.
• Reducing the Dimensionality of Data with Neural Networks
• Reverse-Engineering Neural Networks to Characterize Their Cost Functions
• Universal approximation bounds for superpositions of a sigmoidal function
• Globally Convergent Deflationary Instantaneous Blind Source Separation Algorithm for Digital Communication Signals
• On the Convergence of ICA Algorithms With Symmetric Orthogonalization
• Spiking Neuron Models
• A Unifying Framework of Synaptic and Intrinsic Plasticity in Neural Populations
• Blind Nonnegative Source Separation Using Biological Neural Networks
• Approximation by superpositions of a sigmoidal function

This page was built for publication: On the Achievability of Blind Source Separation for High-Dimensional Nonlinear Source Mixtures