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.

background or methods

/pdf/an-information-maximization-approach-to-blind-separation-and-1cnlj7ibol.pdf

Adaptive filter theory (2nd ed.)

An information-maximization approach to blind separation and blind deconvolution

Broadband wireless access systems deployed in residential and business environments are likely to face hostile radio propagation environments, with multipath delay spread extending over tens or hundreds of bit intervals. Orthogonal frequency-division multiplex (OFDM) is a recognized multicarrier solution to combat the effects of such multipath conditions. This article surveys frequency domain equalization (FDE) applied to single-carrier (SC) modulation solutions. SC radio modems with frequency domain equalization have similar performance, efficiency, and low signal processing complexity advantages as OFDM, and in addition are less sensitive than OFDM to RF impairments such as power amplifier nonlinearities. We discuss similarities and differences of SC and OFDM systems and coexistence possibilities, and present examples of SC-FDE performance capabilities.

/pdf/frequency-domain-equalization-for-single-carrier-broadband-17aswqzbww.pdf

Frequency domain equalization for single-carrier broadband wireless systems

Fundamental and advanced developments in neuro-fuzzy synergisms for modeling and control are reviewed. The essential part of neuro-fuzzy synergisms comes from a common framework called adaptive networks, which unifies both neural networks and fuzzy models. The fuzzy models under the framework of adaptive networks is called adaptive-network-based fuzzy inference system (ANFIS), which possess certain advantages over neural networks. We introduce the design methods for ANFIS in both modeling and control applications. Current problems and future directions for neuro-fuzzy approaches are also addressed. >

https://ir.nctu.edu.tw:443/bitstream/11536/2013/1/A1995QJ99800003.pdf

Neuro-fuzzy modeling and control

artificial neural networks , artificial neural networks , مرکز فناوری اطلاعات و اطلاع رسانی کشاورزی

Artificial Neural Networks

From the Publisher:
Kalman filtering is a well-established topic in the field of control and signal processing and represents by far the most refined method for the design of neural networks. This book takes a nontraditional nonlinear approach and reflects the fact that most practical applications are nonlinear. The book deals with important applications in such fields as control, financial forecasting, and idle speed control.

Adaptive filter theory (2nd ed.)

Citations

An information-maximization approach to blind separation and blind deconvolution

Frequency domain equalization for single-carrier broadband wireless systems

Neuro-fuzzy modeling and control

Artificial Neural Networks

Kalman Filtering and Neural Networks

Related Papers (5)

Adaptive Filter Theory

Digital Communications

Adaptive Signal Processing

Microwave Mobile Communications

Neural Networks: A Comprehensive Foundation