IEEE Computational Intelligence Magazine - February 2020 - 21

learning, based on a well-recognized firstperson perspective game Doom."
IEEE Transactions on Cognitive
and Developmental Systems

Deep Spiking Convolutional Neural
Network Trained With Unsupervised
Spike-Timing-Dependent Plasticity, by
C. Lee, G. Srinivasan, P. Panda, and K.
Roy, IEEE Transactions on Cognitive
and Developmental Systems, Vol. 11,
No. 3, September 2019, pp. 384-394.
Digital Object Identifier: 10.1109/
TCDS.2018.2833071
"Spiking neural networks (SNNs)
have emerged as a promising brain inspired neuromorphic-computing paradigm for cognitive system design due to
their inherent event-driven processing
capability. The fully connected (FC)
shallow SNNs typically used for pattern
recognition require large number of
trainable parameters to achieve competitive classification accuracy. In this paper,
the authors propose a deep spiking convolutional neural network (SpiCNN)
composed of a hierarchy of stacked convolutional layers followed by a spatialpooling layer and a final FC layer. The
network is populated with biologically
plausible leaky-integrate-and-fire (LIF)
neurons interconnected by shared synaptic weight kernels. The authors train
convolutional kernels layer-by-layer in
an unsupervised manner using spiketiming-dependent plasticity (STDP) that
enables them to self-learn characteristic

features making up the input patterns. In
order to further improve the feature
learning efficiency, the authors propose
using smaller 3 × 3 kernels trained using
STDP-based synaptic weight updates
performed over a mini-batch of input
patterns. The proposed deep SpiCNN,
consisting of two convolutional layers
trained using the unsupervised convolutional STDP learning methodology,
achieved classification accuracies of
91.1% and 97.6%, respectively, for inferr ing handwr itten digits from the
MNIST data set and a subset of natural
images from the Caltech data set."
IEEE Transactions on Emerging
Topics in Computational
Intelligence

Data-Driven Decision-Making (D3M):
Framework, Methodology, and Directions,
by J. Lu, Z.Yan, J. Han, and G. Zhang,
IEEE Transactions on Emerging Topics in
Computational Intelligence, Vol. 3, No.
4, August 2019, pp. 286-296.
Digital Object Identifier: 10.1109/
TETCI.2019.2915813
"A decision problem, according to
traditional principles, is approached by
finding an optimal solution to an analytical programming decision model,
which is known as model-driven decision-making. The fidelity of the model
determines the quality and reliability of
the decision-making; however, the
intrinsic complexity of many real-world
decision problems leads to significant

model mismatch or infeasibility in
deriving a model using the first principle. To overcome the challenges that
are present in the big data era, both
researchers and practitioners emphasize
the importance of making decisions
that are backed up by data related to
decision tasks, a process called datadriven decision-making (D 3M). By
building on data science, not only can
decision models be predicted in the
presence of uncertainty or unknown
dynamics, but also inherent rules or
knowledge can be extracted from data
and directly utilized to generate decision solutions. This position paper systematically discusses the basic concepts
and prevailing techniques in data-driven
decision-making and clusters-related
developments in technique into two
main categories: programmable datadriven decision-making (P-D3M) and
nonprogrammable data-driven decision-making (NP-D 3M). This paper
establishes a D3M technical framework,
main methodologies, and approaches
for both categories of D3M, as well as
identifies potential methods and procedures for using data to support decision-making. It also provides examples
of how D3M is implemented in practice
and identifies five further research
directions in the D3M area. We believe
that this paper will directly support
researchers and professionals in their
understanding of the fundamentals of
D3M and of the developments in technical methods."

Call for Papers for Journal Special Issues
Special Issue on "Applications of Fuzzy Systems in Data Science and Big Data"
Journal: IEEE Transactions on Fuzzy Systems
Guest Editors: Gautam Srivastava, Dragan Pamučar, Jerry Chun-Wei Lin, and Sotiris Kotsiantis
Submission Deadline: March 1, 2020
Further Information: Gautam Srivastava (srivastavag@brandonu.ca)

https://cis.ieee.org/images/files/Publications/TFS/special-issues/A_Special_Session_on_Applications_of_Fuzzy_S
ystems_in_Data_Science_and_Big_Data.pdf
Digital Object Identifier 10.1109/MCI.2019.2954684

FEBRUARY 2020 | IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE

https://cis.ieee.org/images/files/Publications/TFS/special-issues/A_Special_Session_on_Applications_of_Fuzzy_Systems_in_Data_Science_and_Big_Data.pdf https://cis.ieee.org/images/files/Publications/TFS/special-issues/A_Special_Session_on_Applications_of_Fuzzy_Systems_in_Data_Science_and_Big_Data.pdf

IEEE Computational Intelligence Magazine - February 2020

Table of Contents for the Digital Edition of IEEE Computational Intelligence Magazine - February 2020