[图书][B] Modern signal processing
XD Zhang - 2022 - books.google.com
The book systematically introduces theories of frequently-used modern signal processing
methods and technologies, and focuses discussions on stochastic signal, parameter …
methods and technologies, and focuses discussions on stochastic signal, parameter …
Efficient backprop
The convergence of back-propagation learning is analyzed so as to explain common
phenomenon observedb y practitioners. Many undesirable behaviors of backprop can be …
phenomenon observedb y practitioners. Many undesirable behaviors of backprop can be …
Natural gradient works efficiently in learning
SI Amari - Neural computation, 1998 - ieeexplore.ieee.org
When a parameter space has a certain underlying structure, the ordinary gradient of a
function does not represent its steepest direction, but the natural gradient does. Information …
function does not represent its steepest direction, but the natural gradient does. Information …
[图书][B] Adaptive blind signal and image processing: learning algorithms and applications
A Cichocki, S Amari - 2002 - books.google.com
With solid theoretical foundations and numerous potential applications, Blind Signal
Processing (BSP) is one of the hottest emerging areas in Signal Processing. This volume …
Processing (BSP) is one of the hottest emerging areas in Signal Processing. This volume …
An adaptive deep reinforcement learning framework enables curling robots with human-like performance in real-world conditions
The game of curling can be considered a good test bed for studying the interaction between
artificial intelligence systems and the real world. In curling, the environmental characteristics …
artificial intelligence systems and the real world. In curling, the environmental characteristics …
[图书][B] Evolving connectionist systems: the knowledge engineering approach
NK Kasabov - 2007 - books.google.com
This second edition of the must-read work in the field presents generic computational
models and techniques that can be used for the development of evolving, adaptive modeling …
models and techniques that can be used for the development of evolving, adaptive modeling …
Adaptive blind signal processing-neural network approaches
S Amari, A Cichocki - Proceedings of the IEEE, 1998 - ieeexplore.ieee.org
Learning algorithms and underlying basic mathematical ideas are presented for the problem
of adaptive blind signal processing, especially instantaneous blind separation and …
of adaptive blind signal processing, especially instantaneous blind separation and …
A unifying information-theoretic framework for independent component analysis
We show that different theories recently proposed for independent component analysis (ICA)
lead to the same iterative learning algorithm for blind separation of mixed independent …
lead to the same iterative learning algorithm for blind separation of mixed independent …
[图书][B] Evolving connectionist systems: Methods and applications in bioinformatics, brain study and intelligent machines
N Kasabov - 2013 - books.google.com
Many methods and models have been proposed for solving difficult problems such as
prediction, planning and knowledge discovery in application areas such as bioinformatics …
prediction, planning and knowledge discovery in application areas such as bioinformatics …