Computational Intelligence - February 2016 - 15

Publication
Spotlight

Haibo He, Chin-Teng Lin,
Kay Chen Tan, Graham Kendall,
and Angelo Cangelosi

CIS Publication Spotlight

IEEE Transactions on Neural
Networks and Learning Systems

Approximate N-Player Nonzero-Sum
Game Solution for an Uncertain Continuous Nonlinear System, by M. Johnson,
R. Kamalapurkar, S. Bhasin, and W. E.
Dixon, IEEE Transactions on Neural
Networks and Learning Systems,Vol. 26,
No. 8, August 2015, pp. 1645-1658.
Digital Object Identifier: 10.1109/
TNNLS.2014.2350835
"An approximate online equilibrium
solution is developed for an N-player
nonzero-sum game subject to continuous-time nonlinear unknown dynamics
and an infinite horizon quadratic cost. A
novel actor-critic-identifier structure is
used, wherein a robust dynamic neural
network is used to asymptotically identify the uncertain system with additive
disturbances, and a set of critic and
actor neural networks (NNs) are used
to approximate the value functions and
equilibrium policies, respectively. The
weight update laws for the actor NNs
are generated using a gradient-descent
method, and the critic NNs are generated by least square regression, which
are both based on the modified Bellman error that is independent of the
system dynamics. A Lyapunov-based
stability analysis shows that uniformly
ultimately bounded tracking is achieved,
and a convergence analysis demonstrates
that the approximate control policies
Digital Object Identifier 10.1109/MCI.2015.2502127
Date of publication: 13 January 2016

scheme based on a
smoothing proximal gradient method. When trained
on unlabeled video sequences, the model learns a
hierarchy of stable attractors, representing low-level
to high-level parts of the
objects. The authors demonstrate that the model
effectively utilizes contextual information to
image licensed by masterseries
produce robust and stable representations for object recognition
Context Dependent Encoding Using
in video sequences, even in case of highConvolutional Dynamic Networks, by
ly corrupted inputs."
R. Chalasani and J. C. Principe, IEEE
Transactions on Neural Networks and
Learning Systems, Vol. 26, No. 9, SepIEEE Transactions on Fuzzy Systems
tember 2015, pp. 1992-2004.
Dynamic Tanker Steering Control Using
Digital Object Identifier: 10.1109/
Generalized Ellipsoidal-Basis-FunctionTNNLS.2014.2360060
Based Fuzzy Neural Networks, by N.
"Perception of sensory signals is
Wang, M. J. Er, and M. Han, IEEE
strongly influenced by their context,
Transactions on Fuzzy Systems, Vol. 23,
both in space and time. In this paper, the
No. 5, October 2015, pp. 1414-1427.
authors propose a novel hierarchical
model, called convolutional dynamic
Digital Object Identifier: 10.1109/
networks, that effectively utilizes this
TFUZZ.2014.2362144
contextual information, while inferring
"This paper deals with tanker steerthe representations of the visual inputs.
ing control based on a novel multipleThe authors build this model based on a
input multiple-output generalized ellippredictive coding framework and use
soidal-basis-function-based fuzzy neural
the idea of empirical priors to incorponetwork (GEBF-FNN) with online
rate recurrent and top-down connecupdating of system structure and paramtions. These connections endow the
eters. The main contributions of this
model with contextual information
paper are as follows. (1) A GEBF-FNNcoming from temporal as well as abstract
based nonlinear steering model incorpoknowledge from higher layers. To perrating the nonlinearity underlying tanker
form inference efficiently in this hierardynamics is proposed. (2) The static local
chical model, the authors rely on a novel
controller (SLC), whose controller gains

converge to a neighborhood of the optimal
solutions. The actor,
cr itic, and identifier
structures are implemented in real time continuously and simultaneously. Simulations on
two and three player
games illustrate the performance of the developed method."

February 2016 | Ieee ComputatIonal IntellIgenCe magazIne

Table of Contents for the Digital Edition of Computational Intelligence - February 2016