The DOI matches its Crossref record; 53 of the 53 references it cites were found in a registry or an index.
An Information-Maximization Approach to Blind Separation and Blind Deconvolution
Abstract
We derive a new self-organizing learning algorithm that maximizes the information transferred in a network of nonlinear units. The algorithm does not assume any knowledge of the input distributions, and is defined here for the zero-noise limit. Under these conditions, information maximization has extra properties not found in the linear case (Linsker 1989). The nonlinearities in the transfer function are able to pick up higher-order moments of the input distributions and perform something akin to true redundancy reduction between units in the output representation. This enables the network to separate statistically independent components in the inputs: a higher-order generalization of principal components analysis. We apply the network to the source separation (or cocktail party) problem, successfully separating unknown mixtures of up to 10 speakers. We also show that a variant on the network architecture is able to perform blind deconvolution (cancellation of unknown echoes and reverberation in a speech signal). Finally, we derive dependencies of information transfer on time delays. We suggest that information maximization provides a unifying framework for problems in "blind" signal processing.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Subsequently, extended infomax independent components analysis (ICA)63,64 was applied to detect eye movement-related artifacts.”
From Event-related potentials of automatic imitation are modulated by ethnicity during stimulus processing, but not during motor execution (2018) · cites this paper as [63]
In the citing paper
“Independent component analysis (ICA) decomposes the observed response into a linear mixture of non-Gaussian causes [36].”
From Hierarchical Models in the Brain (2008) · cites this paper as [36]
In the citing paper
“Next, we ran the Infomax ICA algorithm [Bell and Sejnowski, 1995], repeating it 15 times in ICASSO, implemented in GIFT, to generate a stable set of 75 final components.”
From Specific default mode subnetworks support mentalizing as revealed through opposing network recruitment by social and semantic FMRI tasks: Mentalizing and Default-Mode Subnetworks (2015) · cites this paper as Bell and Sejnowski, 1995
Citations
Cites
Neural Networks: A Comprehensive Foundation
Haykin, S. (1998) · Cited by 30,070
Probability, Random Variables, and Stochastic Processes.
Abrahams, J., & Papoulis, A. (1984) · Journal of the American Statistical Association · doi:10.2307/2288754 · Cited by 16,301
Independent component analysis, A new concept?
Comon, P. (1994) · Signal Processing · doi:10.1016/0165-1684(94)90029-9 · Cited by 8,324
A Fast Fixed-Point Algorithm for Independent Component Analysis
Hyvärinen, A., & Erkki Oja, A. (1997) · Neural Computation · doi:10.1162/neco.1997.9.7.1483 · Cited by 3,373
Blind separation of sources, part I: An adaptive algorithm based on neuromimetic architecture
Jutten, C., & Hérault, J. (1991) · Signal Processing · doi:10.1016/0165-1684(91)90079-x · Cited by 2,550
Adaptive filter theory (2nd ed.)
Haykin, S. (1991) · Prentice-Hall, Inc eBooks · Cited by 1,905
Barlow, H. B. (1989) · The MIT Press eBooks · doi:10.1162/neco.1989.1.3.295 · Cited by 1,709
First- and Second-Order Methods for Learning: Between Steepest Descent and Newton's Method
Battiti, R. (1992) · Neural Computation · doi:10.1162/neco.1992.4.2.141 · Cited by 1,193
What Is the Goal of Sensory Coding?
Field, D. J. (1994) · Neural Computation · doi:10.1162/neco.1994.6.4.559 · Cited by 1,183
A Simple Coding Procedure Enhances a Neuron's Information Capacity
Laughlin, S. B. (1981) · Zeitschrift für Naturforschung C · doi:10.1515/znc-1981-9-1040 · Cited by 1,015
Research works printed but not linked: 1
- Li S., 1994, I E E E J. Oceanic Eng., 20, 73
Cited by
Sorted by citations
Delorme, A., & Makeig, S. (2004) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2003.10.009 · Cited by 24,371
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570
Learning the parts of objects by non-negative matrix factorization
Lee, D. D., & Seung, H. S. (1999) · Nature · doi:10.1038/44565 · Cited by 14,137
A Global Geometric Framework for Nonlinear Dimensionality Reduction
Tenenbaum, J. B., Silva, V. D., & Langford, J. C. (2000) · Science · doi:10.1126/science.290.5500.2319 · Cited by 13,585
$rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation
Aharon, M., Elad, M., & Bruckstein, A. M. (2006) · IEEE Transactions on Signal Processing · doi:10.1109/tsp.2006.881199 · Cited by 9,464
Metadata
- Authors
- Bell, A. J., & Sejnowski, T. J.
- Affiliations
- Howard Hughes Medical Institute (US)
- Howard Hughes Medical Institute, Computational Neurobiology Laboratory, The Salk Institute, 10010 N. Torrey Pines Road, La Jolla, CA 92037 USA and Department of Biology, University of California, San Diego, La Jolla, CA 92093 USA
- ORCID
- Bell, Anthony J.
- Venue
- Neural Computation
- Publisher
- MIT Press
- Published
- 1995-11
- Volume
- 7
- Issue
- 6
- Pages
- 1129-1159
- ISSN
- 0899-7667 (ISSN-L)
- 1530-888X
- OpenAlex
- W2108384452
- Cited by
- 8,986
- References
- 52
- Citations by year
- 2026: 151 · 2025: 242 · 2024: 264 · 2023: 286 · 2022: 329 · 2021: 375 · 2020: 349 · 2019: 372 · 2018: 343 · 2017: 334 · 2016: 346 · 2015: 357 · 2014: 365 · 2013: 352 · 2012: 328
- FWCI
- 130.90
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Neural Computation (publishedVersion)
- PubMed (publishedVersion)
- Funders
- Office of Naval Research
- Topics
- Physical Sciences › Computer Science › Signal Processing › Blind Source Separation Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
- Keywords
- information maximization, blind source separation, blind deconvolution, self-organized learning, nonlinear neural networks, higher-order statistics, redundancy reduction, principal component analysis, cocktail party problem, time delay dependence, blind signal processing
- MeSH terms
- Algorithms, Humans, Learning, Neurons, Probability, Problem Solving, Speech, Models, Statistical, Neural Networks, Computer
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
