(Enter summary)
Abstract: Wederive a new self-organising learning algorithm which maximises
the information transferred in a network of non-linear 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
maximisation has extra properties not found in the linear case
(1se er 1989). The non-linearities in the transfer function are able to
pick up higher-order moments of the input distributions and perform... (Update)
Cited by: More
D Spatial Analysis of fMRI Data - On Word Perception
(Correct)
How to generalize Geometric ICA to higher - Dimensions Fabian Theis
(Correct)
Maximum Entropy and Minimal Mutual Information in a Nonlinear.. - Theis, Lang
(Correct)
Similar documents (at the sentence level):
63.8%: An Information-Maximization Approach to Blind Separation and.. - Bell, Sejnowski (1995)
(Correct)
Active bibliography (related documents): More All
0.5: A Unifying Information-theoretic Framework for.. - Lee, Girolami, Bell, .. (1999)
(Correct)
0.5: Discovery of General Learning Rules for Feedforward Neural.. - Radi, Poli (1999)
(Correct)
0.4: A Non-linear Information Maximisation Algorithm that Performs.. - Sejnowski (1995)
(Correct)
Similar documents based on text:
0.0: Unknown -
(Correct)
Related documents from co-citation: More All
43: A new learning algorithm for blind signal separation
- Amari, Cichocki - 1996
35: Equivariant adaptive source separation
- Cardoso, Laheld - 1996
35: Independent component analysis (context) - Comon - 1994
BibTeX entry: (Update)
A. Bell and T. Sejnowski. An information-maximisation approach to blind separation and blind deconvolution. Neural Comp., 7:1129--1159, 1995. http://citeseer.ist.psu.edu/754019.html More
@misc{ bell95informationmaximisation,
author = "A. Bell and T. Sejnowski",
title = "An information-maximisation approach to blind separation and blind deconvolution",
text = "A. Bell and T. Sejnowski. An information-maximisation approach to blind
separation and blind deconvolution. Neural Comp., 7:1129--1159, 1995.",
year = "1995",
url = "citeseer.ist.psu.edu/754019.html" }
Citations (may not include all citations):
2319
Elements of information theory (context) - Cover, Thomas - 1991
815
Adaptive filter theory (context) - Haykin - 1991
206
Independent component analysis (context) - Comon - 1994
181
random variables and stochastic processes (context) - Probability - 1984
162
What is the goal of sensory coding (context) - Field - 1994
126
Unsupervised learning (context) - Barlow - 1989
97
First- and second-order methods for learning: between steepe..
- Battiti - 1992
93
Possible principles underlying the transformation of sensory.. (context) - Barlow - 1961
91
Could information theory provide an ecological theory of sen.. (context) - Atick - 1992
80
Blind separation of sources (context) - Comon, Jutten et al. - 1991
80
Blind separation of sources (context) - Jutten, Herault - 1991
79
Non-linear neurons in the low noise limit: a factorial code ..
- J-P - 1994
64
Representation and separation of signals using non-linear PC.. (context) - Karhunen, Joutsensalo - 1994
44
Blind separation of sources: a non-linear neural algorithm (context) - Burel - 1992
40
Learning factorial codes by predictability minimisation
- Schmidhuber - 1992
35
A simple coding procedure enhances a neuron's information ca.. (context) - Laughlin - 1981
32
Adaptation and decorrelation in the cortex (context) - Barlow, Foldi'ak - 1989
31
An application of the principle of maximum information prese.. (context) - Linsker - 1989
31
Non-linear higher-order statistical decorrelation byvolume-c.. (context) - Deco, Brauer - 1995
28
Separation of independent signals using time-delayed correla.. (context) - Molgedey, Schuster - 1994
27
Local synaptic learning rules suffice to maximise mutual inf.. (context) - Linsker - 1992
25
Convergent algorithm for sensory receptive field development (context) - Atick, Redlich - 1993
23
Criteria for multichannel signal separation (context) - Yellin, Weinstein - 1994
21
Olfactory computation and object perception (context) - Hopfield - 1991
20
Networks for the separation of sources that are superimposed.. (context) - Platt, Faggin - 1992
19
Space or time adaptive signal processing by neural network m.. (context) - Herault, Jutten - 1986
18
Bussgang techniques for blind deconvolution and equalisation (context) - Bellini - 1994
12
Statistical independence and novelty detection with informat..
- Parra, Deco et al. - 1995
9
Adaptive separation of mixed broadband sound sources with de.. (context) - Li, Sejnowski - 1994
6
Competitivean ti-Hebbian learning of invariants
- Schraudolph, Sejnowski - 1992
6
Current-Mode Subthreshold MOS Implementation of the Herault-.. (context) - Cohen, Andreou - 1992
6
Optimal sampling of natural images: a design principle for t.. (context) - Ruderman, Zee - 1991
5
Blind separation of sources (context) - Sorouchyari - 1991
5
CMOS integration of Herault-Jutten cells for separation of s.. (context) - Vittoz, Arreguit - 1989
4
Optimal information flow in sigmoidal neurons (context) - Schraudolph, Hart et al. - 1991
4
A non-linear information maximisation algorithm that perform..
- Bell, Sejnowski - 1995
4
A self-organising neural network that discovers surfaces in .. (context) - Becker, Hinton - 1992
2
Blind equalisation based on higherorder statistics (context) - Hatzinakos, Nikias - 1994
2
Blind equalisation formulated as a self-organized learning p.. (context) - Haykin - 1992
2
noise breakdown (context) - Learning, the et al. - 1992
2
Analog CMOS integration and experimentation with an autoadap.. (context) - Cohen, Andreou - 1995
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://www-sigproc.eng.cam.ac.uk/research/reading%20group/index.html): More
The Kalman Swarm - New Approach To
(Correct)
On-Line Bayesian Methods For Estimation Of Non-Linear.. - Simon Godsill Signal
(Correct)
Complex Wavelets - For Shift Invariant
(Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC