Paris' Independent Component Analysis & Blind Source Separation page
Independent Component Analysis (ICA) and Blind Source Separation (BSS)
have received quite a lot of attention lately so that I decided to compile
a list of online resources for whoever is interested. By no means is this
page complete and if you have any additions do send me mail at paris at
media dot mit dot edu.
In the papers section I do not list all of the papers of every author (that's
why you should check their homepages) but the really good ones are here.
Also not all ICA & BSS people have home pages so if you discover any
or if I missed yours tell me about it and I'll add them. Also note that this is a pretty ancient page, so expect many links to not work!
People working on ICA & BSS

Alex Westner a
brave man who scoffs at the complexity of realworld mixtures
Other ICA Pages
Benchmarks

Daniël Schobben, Kari Torkkola and me maintain these:
Code and Software ...

The FastICA
package by Aapo Hyvärinen (very cool, get it!)

By JeanFrançois Cardoso:

RICA by
Cichocki and Barros.

By me:

Mostly old instantaneous ICA code (in
MATLAB)
Online Demos of BSS

Barak Pearlmutter's Demo
on Contextual ICA

My little frequency domain algorithm:
(This is actually a
static mix, I just put it up cause it sounds cool, but the algorithm can deal with
convolved mixtures too)

Hans van Hateren's demo
on images.
Online Papers on ICA & BSS
(since I don't really sit around all day playing with this page, there some links that are
extinct by now. Rather than giving up, check out the home page of the corresponding author in
the top of the page. You are most likely to find their papers there. You are also most
likely to find their newer papers there too).

Yes, I actually finished my dissertation!
 Smaragdis, P. 2001. Redundancy reduction for
computational
audition, a unifying approach. Ph.D. dissertation, MAS
department, Massachusetts Institute of Technology.

Smaragdis, P. 1997. Information
Theoretic Approaches to Source Separation, Masters Thesis, MAS
Department, Massachusetts Institute of Technology.
I realize that the name of the thesis is not terribly enlightening.
What happens in there, apart from the obligatory background stuff, is the
development of a new frequency domain separation algorithm to deal with
convolved mixtures. The idea is to move to a space where the separation
parameters are orthogonal, to assist convergence, and to be able to implement
at the same time faster convolution schemes. In addition to this the algorithm
is online and realtime so that you can actually use it. Results are nice
too!

Smaragdis, P. 1997. Efficient
Blind Separation of Convolved Sound Mixtures,IEEE ASSP Workshop on
Applications of Signal Processing to Audio and Acoustics. New Paltz NY,
October 1997.
Pretty much the same material, geared towards DSPheads. Written before
my thesis so it is a little outdated.

Smaragdis, P. 1998. Blind
Separation of Convolved Mixtures in the Frequency Domain. International
Workshop on Independence & Artificial Neural Networks University of
La Laguna, Tenerife, Spain, February 9  10, 1998.
Condenced version of my thesis. Most up to date compared to my other
offerings.

Tony Bell has some neat papers on Blind Source Separation:
And a couple of papers on ICA alone:

Kari Torkkola has some practical papers on simultaneous Blind Source
Separation and Deconvolution:

Torkkola, K.:Blind
Separation of Delayed Sources Based on Information Maximization. Proceedings
of the IEEE Conference on Acoustics, Speech and Signal Processing,
May 710 1996, Atlanta, GA, USA.

Torkkola, K.:Blind
Separation of Convolved Sources Based on Information Maximization.
IEEE
Workshop on Neural Networks for Signal Processing, Sept 46 1996, Kyoto,
Japan.

Torkkola, K.:IIR
Filters for Blind Deconvolution Using Information Maximizationrm. NIPS96
Workshop: Blind Signal Processing and Their Applications, Snowmaas
(Aspen), Colorado.

Barak Pearlmutter has a paper on context sensitive ICA:

Erkki Oja has papers on PCA, nonlinear PCA and ICA:

Oja, E., Karhunen, J., Wang, L., and Vigario, R.:Principal
and independent components in neural networks  recent developments.
Proc.
VII Italian Workshop on Neural Nets WIRN'95, May 18  20, 1995, Vietri
sul Mare, Italy (1995).

Oja, E.:The nonlinear
PCA learning rule and signal separation  mathematical analysis. Helsinki
University of Technology, Laboratory of Computer and Information Science,
Report
A26 (1995).

Oja, E. and Taipale, O.:Applications
of learning and intelligent systems  the Finnish technology programme.
Proc.
Int. Conf. on Artificial Neural Networks ICANN95, Industrial Conference,
Oct. 9  13, 1995, Paris, France (1995).

Oja, E.: PCA, ICA,
and nonlinear Hebbian learning. Proc. Int. Conf. on Artificial Neural
Networks ICANN95, Oct. 9  13, 1995, Paris, France, pp. 89  94 (1995).

Oja, E. and Karhunen, J.:Signal
separation by nonlinear Hebbian learning. In M. Palaniswami, Y. Attikiouzel,
R. Marks II, D. Fogel, and T. Fukuda (Eds.), Computational Intelligence
 a Dynamic System Perspective. New York: IEEE Press, pp. 83  97 (1995).

Juha Karhunen has written ICA & BSS papers with Oja (right above)
and some on his own:

Karhunen, J.:Neural
Approaches to Independent Component Analysis and Source Separation.
To
appear in Proc. 4th European Symposium on Artificial Neural Networks (ESANN'96),
April 24  26, 1996, Bruges, Belgium (invited paper).

Karhunen, J., Wang, L., and Vigario, R.,Nonlinear
PCA Type Approaches for Source Separation and Independent Component AnalysisProc.
of the 1995 IEEE Int. Conf. on Neural Networks (ICNN'95), Perth, Australia,
November 27  December 1, 1995, pp. 9951000.

Karhunen, J., Wang, L., and Joutsensalo, J.,Neural
Estimation of Basis Vectors in Independent Component Analysis Proc.
of the Int. Conf. on Artificial Neural Networks (ICANN'95), Paris,
France, October 913, 1995, pp. 317322.

Andrzej Cichocki organized a special invited session on BSS in Nolta
'95 and has a nice list of papers on the subject:
(another apparently defunct set of links ...)

Shunichi Amari, Andrzej Cichocki and Howard Hua Yang, "Recurrent
Neural Networks for Blind Separation of Sources", , pp.3742.

Anthony J. Bell and Terrence J. Sejnowski, "Fast
Blind Separation based on Information Theory", pp. 4347.

Adel Belouchrani and JeanFrancois Cardoso, "Maximum
Likelihood Source Separation by the ExpectationMaximization Technique:
Deterministic and Stochastic Implementation", pp.4953.

JeanFrancois Cardoso, "The
Invariant Approach to Source Separation", pp. 5560.

Andrzej Cichocki, Wlodzimierz Kasprzak and Shunichi Amari, "MultiLayer
Neural Networks with Local Adaptive Learning Rules for Blind Separation
of Source Signals", , pp.6165.

Yannick Deville and Laurence Andry, "Application
of Blind Source Separation Techniques to MultiTag Contactless Identification
Systems", , pp. 7378.

Jie Huang , Noboru Ohnishi and Naboru Sugie "Sound
SeparatioN Based on Perceptual Grouping of Sound Segments", , pp.6772.

Christian Jutten and JeanFrancois Cardoso, "Separation
of Sources: Really Blind ?" , pp. 7984.

Kiyotoshi Matsuoka and Mitsuru Kawamoto, "Blind Signal Separation Based
on a Mutual Information Criterion", pp. 8591.

Lieven De Lathauwer, Pierre Comon, Bart De Moor and Joos Vandewalle,
"HigherOrder
Power Method  Application in Independent Component Analysis" ,
pp. 9196.

Jie Zhu, XiRen Cao, and RueyWen Liu, "Blind
Source Separation Based on Output Independence  Theory and Implementation"
,
pp. 97102.
Papers are included in Proceedings 1995 International Symposium
on Nonlinear Theory and Applications NOLTA'95, Vol.1, NTA Research
Society of IEICE, Tokyo, Japan, 1995.

Shunichi Amari wrote some excelent papers with the RIKEN people on
BSS and the math behind it:

S. Amari, A. Cichocki and H. H. Yang, A
New Learning Algorithm for Blind Signal Separation (128K), In: Advances
in Neural Information Processing Systems 8, Editors D. Touretzky, M. Mozer,
and M. Hasselmo, pp.??(to appear), MIT Press, Cambridge MA, 1996.

Shunichi Amari, Neural
Learning in Structured Parameter Spaces , NIPS'96

Shunichi Amari, Information
Geometry of Neural Networks  New Bayesian Duality Theory  , ICONIP'96

Shunichi Amari, Gradient
Learning in Structured Parameter Spaces: Adaptive Blind Separation of Signal
Sources , WCNN'96

Shunichi Amari and JeanFrancois Cardoso, Blind
Source Separation  Semiparametric Statistical Approach, sumitted to
IEEE Tr. on Signal Processing.

Shunichi Amari, Natural
Gradient Works Efficiently in Learning, sumitted to Neural Computation.

Howard Hua Yang and Shunichi Amari, Adaptive
OnLine Learning Algorithms for Blind Separation  Maximum Entropy and
Minimum Mutual Information , accepted for Neural Computation.

Shunichi Amari, TianPing CHEN, Andrzej CICHOCKI, Stability
Analysis of Adaptive Blind Source Separation , accepted for Neural
Neworks.

Shunichi Amari, Superefficiency
in Blind Source Separation , sumitted to IEEE Tr. on Signal Processing.

Shunichi Amari and Noboru Murata, Statistical
Analysis of Regularization Constant  From Bayes, MDL and NIC Points of
View, International WorkDonf. on Artificial and Natural Neural Networks
97.

Shunichi Amari,
Geometry of Semiparametric Models and Applications , ISI'97

JeanFrançois Cardoso has lots (and lots, and lots, ...) of papers on
BSS!

JeanFrançois Cardoso and Beate Laheld. Equivariant
adaptive source separation. To appear in IEEE Trans. on S.P.

JeanFrançois Cardoso. Performance
and implementation of invariant source separation algorithms In Proc.
ISCAS'96, 1996.

JeanFrançois Cardoso, Sandip Bose, and Benjamin Friedlander. On
optimal source separation based on second and fourth order cumulants
In Proc. IEEE Workshop on SSAP, Corfou, Greece, 1996.

JeanFrançois Cardoso. The
equivariant approach to source separation In Proc. NOLTA, pages
5560, 1995.

JeanFrançois Cardoso. Séparation
de sources dans l'espace signal In Proc. GRETSI, Juan les Pins,France,
1995.

JeanFrançois Cardoso. A
tetradic decomposition of 4thorder tensors: application to the source
separation problem In M. Moonen and B. de Moor, editors, Algorithms,
architectures and applications, volume III of SVD and signal processing,
pages 375382. Elsevier, 1995.

JeanFrançois Cardoso, Sandip Bose, and Benjamin Friedlander. Output
cumulant matching for source separation In Proc. IEEE SP Workshop
on HigherOrder Stat., Aiguablava, Spain, pages 4448, 1995.

Adel Belouchrani and JeanFrançois Cardoso. Maximum
likelihood source separation for discrete sources In Proc. EUSIPCO,
pages 768771, Edinburgh, September 1994.

JeanFrançois Cardoso. On
the performance of source separation algorithms In Proc. EUSIPCO,
pages 776779, Edinburgh, September 1994.

JeanFrançois Cardoso, Adel Belouchrani, and Beate Laheld. A
new composite criterion for adaptive and iterative blind source separation
In Proc. ICASSP, volume 4, pages 273276, April 1994.

Beate Laheld and JeanFrançois Cardoso. Adaptive
source separation with uniform performance In Proc. EUSIPCO,
pages 183186, Edinburgh, September 1994.

JeanFrançois Cardoso and Antoine Souloumiac. An
efficient technique for blind separation of complex sources In Proc.
IEEE SP Workshop on HigherOrder Stat., Lake Tahoe, USA, pages 275279,
1993.

JeanFrançois Cardoso. Iterative
techniques for blind source separation using only fourth order cumulants
In Proc. EUSIPCO, pages 739742, 1992.

JeanFrançois Cardoso and Beate Laheld. Adaptive blind source separation
for channel spatial equalization In Proc. of COST 229 workshop on adaptive
signal processing, pages 1926, 1992.

JeanFrançois Cardoso. Eigenstructure
of the fourthorder cumulant tensor with application to the blind source
separation problem In Proc. ICASSP, pages 26552658, 1990.

JeanFrançois Cardoso. Source
separation using higher order moments In Proc. ICASSP, pages
21092112, 1989.

JeanFrançois Cardoso and Pierre Comon. Independent
component analysis, a survey of some algebraic methods In Proc.
ISCAS'96, vol.2, pp. 9396, 1996.

JeanFrançois Cardoso, Infomax
and maximum likelihood for source separation,. To appear in IEEE Letters
on Signal Processing, April, 1997.

Cichocki & Kasprzak have a nice collection of papers:

Cichocki A., Kasprzak W.: Nonlinear
Learning Algorithms for Blind Separation of Natural Images , Neural
Network World, vol.6, 1996, No.4, IDG Co., Prague, 515523.

Cichocki A., Kasprzak W., Amari S.I.: Neural
Network Approach to Blind Separation And Enhancement of Images ,
EUSIPCO'96
, (Trieste, Italy, September 1996).

Kasprzak W., Cichocki A.: Hidden
Image Separation From Incomplete Image Mixtures by Independent Component
Analysis , ICPR'96 , Vienna, August 1996.

Cichocki A., Amari S., Adachi M., Kasprzak W.: SelfAdaptive
Neural Networks for Blind Separation of Sources , 1996 IEEE
International Symposium on Circuits and Systems, ISCAS'96, Vol. 2,
IEEE, Piscataway, NJ, 1996, 157160.

Mark Girolami at University of Paisley has some papers too:

Girolami, M and Fyfe, C.
Blind Separation of Sources Using Exploratory Projection Pursuit Networks.
Speech
and Signal Processing, International Conference on the Engineering Applications
of Neural Networks, ISBN 9529075170, London, pp249252, 1996.

Girolami, M and Fyfe, C.
Higher Order Cumulant Maximisation Using Nonlinear Hebbian and AntiHebbian
Learning for Adaptive Blind Separation of Source Signals, Proc IWSIP96,
IEEE/IEE International Workshop on Signal and Image Processing, Advances
in Computational Intelligence, Elsevier Science, pp141  144, Manchester,
47 November 1996.

Girolami, M and Fyfe, C.
Multivariate Density Factorisation for Independent Component Analysis :
An Unsupervised Artificial Neural Network Approach, AISTATS97,
3'rd International Workshop on Artificial Intelligence and Statistics,
Fort Lauderdale, Florida, Jan 1997.

Girolami, M and Fyfe, C.
Negentropy and Kurtosis as Projection Pursuit Indices Provide Generalised
ICA Algorithms, NIPS96 Blind Signal Separation Workshop, (Org A.
Cichocki & A.Back), Aspen, Colorado, 7 Dec, 1996.

Girolami, M and Fyfe, C.
A Temporal Model of Linear AntiHebbian Learning, Neural Processing
Letters, In Press Vol 4, Issue 3, Jan 1997.

TeWon Lee at the Salk Institute has some interesting papers:

Blind
separation of delayed and convolved sources, T.W. Lee and A.J. Bell
and R. Lambert, accepted for publication in "Advances in Neural
Information Processing Systems", MIT Press, Cambridge MA, 1996

Blind
Source Separation of Real World Signals, T.W. Lee, A.J. Bell and
R. Orglmeister, to appear in "IEEE International Conference Neural
Networks ", Houston, 1997

Juergen Schmidhuber at IDSIA has related papers:

Henrik Sahlin's papers on separation and second order statistics:

H. Broman, U. Lindgren, H. Sahlin and P. Stoica
``Source
Separation: A TITO system identification approach'', Tech. rep. CTHTE33,
Department of Applied Electronics, Chalmers University of Technology, Sept.
1995, Submitted to IEEE Trans. SP.

H. Sahlin and U. Lindgren "The
Asymptotic CramerRao Lower Bound for Blind Signal Separation". "The
Proceedings of the 8th IEEE Signal Processing Workshop on Statistical Signal
and Array Processing", Corfu, Greece, 1996

H. Sahlin "Asymptotic
parameter variance analysis for Blind Signal Separation" "The proceedings
of RVK96", Lulea, Sweden, 1996

H. Sahlin and H. Broman "Blind
Separation of Images" "The Proceedings of Asilomar Conference on Signals,
Systems, and Computers", Pacific Grove, CA, USA, 1996.

U. Lindgren, H. Sahlin and H. Broman
"Source
separation using second order statistics" "The Proceedings of EUSIPCO96",
Trieste, Italy, 1996.

H. Sahlin, U. Lindgren and H. Broman
"Multi
Input Multi Output Blind Signal Separation Using Second Order Statistics"
Tech. rep. CTHTE54, Department of Applied Electronics, Chalmers University
of Technology, Dec., 1996.

H. Sahlin
"On
Signal Separation by Second Order Statistics" Licentiate Thesis, Technical
Report No. 251L, Department of Applied Electronics, Chalmers University
of Technology, 1997.

H. Sahlin and H. Broman
"Signal
Separation Applied to Real World Signals" Proceedings of International
Workshop on Accoustic Echo and Noise Control, London, UK, September,1997.

Gustavo Deco and Dragan Obradovic have an excellent book on ICA and
related matters:

Kevin Knuth on ICA:

Bayesian
source separation and localization. To be published in: SPIE'98
Proceedings: Bayesian Inference for Inverse Problems, San Diego, July 1998.
[pdf
475K], [doc
500K].

Knuth K.H. 1999. A Bayesian approach to source separation. In: J.F.
Cardoso, C. Jutten and P. Loubaton (eds.), Proceedings of the First
International Workshop on Independent Component Analysis and Signal
Separation: ICA'99, Aussios, France, Jan. 1999, pp. 283288.
 Knuth K.H. and Vaughan H.G., Jr. 1998.
Convergent Bayesian formulations of
blind source separation and electromagnetic source estimation. Presented
at the MaxEnt98 workshop in Munich, July 1998.

Alex Westner has worked on real world experiments:
 Roberto Manduchi on ICA and textures:
 Lucas Parra:
 Lucas Parra, Clay Spence, "Online convolutive source separation
of nonstationary signals", Journal of VLSI Signal Processing,
Special issue on the 1998 IEEE Neural Networks and Signal Processing
Workshop, to appear in summer 2000, (.ps.gz
249K, .pdf 482K)
 Lucas Parra, KlausRobert Mueller, Clay Spence, Andreas Ziehe,
Paul Sajda, "Unmixing Hyperspectral Data", Advances in Neural Information Processing Systems 12, MIT
Press, to appear 1999. (.ps.gz 76K)
 Simone Fiori has some papers on ICA by the adaptive activation
function networks and learning on StiefelGrassman manifold:
 S. Fiori,
"Entropy Optimization by the PFANN Network: Application to
Independent Component Analysis", Network: Computation in Neural Systems,
Vol. 10, No. 2, pp. 171  186, May 1999
 S. Fiori,
"'Mechanical' Neural
Learning for Blind Source Separation",
Electronics Letters, Vol. 35, No. 22, pp. 1963  1964, Oct. 1999
 S. Fiori, "Blind Separation of
Circularly
Distributed Source Signals
by the Neural Extended APEX Algorithm", Neurocomputing, Vol. 34, No. 14,
pp. 239  252, August 2000
 S. Fiori, "Blind Signal Processing by
the Adaptive Activation Function
Neurons", Neural Networks, Vol. 13, No. 6, pp. 597  611, August 2000
 S. Fiori, "A Theory for Learning by
Weight Flow on StiefelGrassman
Manifold", Neural Computation. Accepted for publication: To appear.
Paris Smaragdis
MIT Media Lab
20 Ames Street, Rm E15401
Cambridge, MA 02139