Computational Intelligence - February 2013 - 9

Publication
Spotlight

Derong Liu, Chin-Teng Lin,
Garry Greenwood, Simon Lucas,
and Zhengyou Zhang

CIS Publication Spotlight

IEEE Transactions on Neural
Networks and Learning Systems

Neural-Fitted TD-Leaf Learning for Playing Othello with Structured Neural Networks, by S. van den Dries and M.A.
Wiering, IEEE Transactions on Neural
Networks and Learning Systems, Vol. 23,
No. 11, Nov. 2012, pp. 1701-1713.
Digital Object Identifier: 10.1109/
TNNLS.2012.2210559
"A methodology for quickly learning to play games at a strong level is
developed. The methodology consists
of a novel combination of three techniques, and a variety of experiments on
the game of Othello demonstrates their
usefulness. Structures or topologies in
neural network connectivity patterns
are used to decrease the number of
learning parameters and to deal more
effectively with the structural credit
assignment problem, which is to
change individual network weights
based on the obtained feedback.
Furthermore, the structured neural
networks are trained with the novel
neural-fitted temporal difference (TD)
learning algorithm to create a system
that can exploit most of the training
exper iences and enhance learning
speed and performance. Finally, the
neural-fitted TD-leaf algorithm is used
to learn more effectively when lookahead search is perfor med by the

Digital Object Identifier 10.1109/MCI.2012.2228582
Date of publication: 14 January 2013

game-playing program. Extensive
experimental study indicated that the
proposed method outperforms linear
networks and fully connected neural
networks or evaluation functions
evolved with evolutionary algorithms."
Nonnegative Blind Source Separation by
Sparse Component Analysis Based on
Determinant Measure, by Zuyuan
Yang, Yong Xiang, Shengli Xie,
Shuxue Ding, and Yue Rong, IEEE
Transactions on Neural Networks and
Learning Systems,Vol. 23, No. 10, Oct.
2012, pp. 1601-1610.
Digital Object Identifier: 10.1109/
TNNLS.2012.2208476
"The problem of nonnegative blind
source separation (NBSS) is studied,
where both the sources and the mixing
matrix are nonnegative and sparse
component analysis is employed.
A determinant-based sparseness measure, named D-measure, is introduced
to gauge the temporal and spatial
sparseness of signals. Based on this measure, a new NBSS model is derived,
and an iterative sparseness maximization (ISM) approach is proposed for
this model. In the ISM approach, the
NBSS problem is solved by row-torow optimizations with respect to the
unmixing matrix, and then the quadratic programming (QP) technique is
used to optimize each row. Furthermore, the source identifiability and the
computational complexity of the proposed ISM-QP method are analyzed.
The new method requires relatively

weak conditions on the sources and the
mixing matrix, has high computational
efficiency, and is easy to implement.
Simulation results demonstrate the
effectiveness of the method."
IEEE Transactions
on Fuzzy Systems

On the Fundamental Differences Between
Interval Type-2 and Type-1 Fuzzy Logic
Controllers, by Wu D., IEEE Transactions
on Fuzzy Systems, Vol. 20, No. 5, Oct.
2012, pp. 832-848.
Digital Object Identifier: 10.1109/
TFUZZ.2012.2186818
"Interval type-2 fuzzy logic controllers (IT2 FLCs) have recently been
attracting a lot of research attention
and many reported results have shown
that IT2 FLCs are better able to handle uncertainties than their type-1
(T1) counterparts. Consequently, the
Author provides two fundamental differences between IT2 and T1 FLCs:
(1) Adaptiveness, meaning that the
embedded T1 fuzzy sets is used to
compute the bounds of the typereduced interval change as input

February 2013 | Ieee ComputatIonal IntellIgenCe magazIne

Table of Contents for the Digital Edition of Computational Intelligence - February 2013