Systems, Man & Cybernetics - April 2017 - 38
◆ Step 1: Rule matched: If C (1) AND f1 ^ x h = - 1 Then
sparse 3VL-MLPs, including the case in which the number
of layers is very large (i.e., a deep-learning model). If we
Add C (7)
(7)
^
h
can obtain a good 3VL-MLP, we can map it directly to an
◆ Step 2: Rule matched: If C AND f4 x = 1 Then
expert system. Through this work, I expect to find a way
Add C (8)
(8)
^
h
for inducing interpretable aware systems directly based
C
◆ Step 3: Rule matched: If
AND f5 x = - 1 Then
on sensory data.
Add C (10)
(10)
C
◆ Step 4: Rule matched: If
Then Output L 5 .
Acknowledgment
Note that since the concept corresponding to the root
I would like to thank the anonymous reviewers for their
node must be true, we should put C (1) into the working
invaluable comments and suggestions.
memory before starting the reasoning process. Also, for
the expert system mapped from a DT, only one rule is
About the Author
matched in each step, and, therefore, conflict resolution is
Qiangfu Zhao (qf-zhao@u-aizu.ac.jp) earned his Ph.D.
not needed.
degree from Tohoku University, Japan, in 1988. He joined
Now, let us review how to map an MLP to an expert
the Department of Electronic Engineering at the Beijing
system. Suppose that the MLP has K (> 1) layers of
Institute of Technology, China, in
neurons (the input layer is not count-
1988, first as a postdoctoral fellow
ed because the input units are not
and then as an associate professor.
neurons but buffers), and the acti-
He was an associate professor
vation function of each neuron is a
If we can obtain a
beginning in October 1993 in the
bipolar sigmoid function. Each
good 3VL-MLP, we
Department of Electronic Engi-
neuron corresponds to an AM. The
neering at Tohoku University,
aware function of the AM can be
can map it directly to
Japan. He joined the University of
defined as the activation function,
an expert system.
Aizu, Japan, in April 1995 as an
and the alert levels Tl and Tu are
associate professor and became a
proper values taken from [−1, 1]
tenured full professor in 1999. His
(e.g., Tl = - 0.5 and Tu = 0.5 ). For
research interests include image
the ith neuron in the kth ^ k 1 K h
processing, pattern recognition, machine learning, and
layer, denoting its output as y ki (x) and the correspond-
awareness computing.
ing concept as C ki, we can map this neuron to the follow-
ing rule:
References
If y ki ^x h = 1 Then Add C ki
[1] G. Chakraborty, R. Kozma, T. Murata, and Q. F. Zhao, "Awareness in brain, society,
and beyond-A bridge connecting raw data to perception and cognition," IEEE
Else if y ki ^x h = - 1 Then Add C ki,
(5)
Syst., Man, and Cybern., vol. 1, no. 3, pp. 8-16, 2015.
where x is the original input from the outside for k = 1 or
the output vector of the ^ k - 1 h -th layer for k 2 1. For the
ith neuron in the Kth layer (i.e., the output layer), denot-
ing its output as y Ki (x) and the corresponding class label
as L i, we can map this neuron to the following rule:
If y Ki ^x h = 1 Then Output L i .
[2] Q. F. Zhao, "Computational awareness: Another way towards intelligence," in
Computational Intelligence, K. Madani, A. Dourado, A. Rosa, and J. Filipe, Eds.
Berlin, Germany: Springer-Verlag, 2013, pp. 3-14.
[3] Q. F. Zhao, "Aware system, aware unit and aware logic," in Proc. 2nd IEEE
Conf. Cybernetics, 2015, pp. 42-47.
[4] Q. F. Zhao, "3VL-MLP: A way for realizing interpretable aware systems," in Proc.
(6)
IEEE Int. Conf. Machine Learning Cybernetics, 2015, pp. 116-122.
[5] J. Searle, "Minds, brains, and programs," Behav. Brain Sci., vol. 3, no. 3, pp.
In pattern recognition, L i is usually a number repre-
senting the label of the ith class.
Using the above process, we can easily map an MLP to
an expert system, provided that each neuron is discretized
to a 3VL-AM based on (1). Using the expert system, we can
conduct recursive reasoning for any given input x.
417-424, 1980.
Conclusion and Remarks
In this article, I introduced a method for mapping an
aware system to an expert system. Recently, I have been
trying to find an efficient and effective way for designing
and Cybern., Syst., vol. 36, no. 3, pp. 520-533, 2006.
[6] S. Harnad, "Category induction and representation," in Categorical Perception:
The Groundwork of Cognition, S. Harnad, Ed. New York: Cambridge University
Press, 1987.
[7] J. R. Quinlan, "Generating rules from decision trees," in Proc. 10th Int. Joint
Conf. Artificial Intelligence, 1987, vol. 1, pp. 304-307.
[8] Q. F. Zhao, "Inducing NNC-trees with the R4-rule," IEEE Trans. Syst., Man,
38
IEEE SyStEmS, man, & CybErnEtICS magazInE A pri l 2017
[9] Q. F. Zhao and T. Higuchi, "Evolutionary learning of nearest neighbor MLP," IEEE
Trans. Neural Netw., vol. 7, no. 3, pp. 762-767, 1996.
Table of Contents for the Digital Edition of Systems, Man & Cybernetics - April 2017
Systems, Man & Cybernetics - April 2017 - Cover1
Systems, Man & Cybernetics - April 2017 - Cover2
Systems, Man & Cybernetics - April 2017 - 1
Systems, Man & Cybernetics - April 2017 - 2
Systems, Man & Cybernetics - April 2017 - 3
Systems, Man & Cybernetics - April 2017 - 4
Systems, Man & Cybernetics - April 2017 - 5
Systems, Man & Cybernetics - April 2017 - 6
Systems, Man & Cybernetics - April 2017 - 7
Systems, Man & Cybernetics - April 2017 - 8
Systems, Man & Cybernetics - April 2017 - 9
Systems, Man & Cybernetics - April 2017 - 10
Systems, Man & Cybernetics - April 2017 - 11
Systems, Man & Cybernetics - April 2017 - 12
Systems, Man & Cybernetics - April 2017 - 13
Systems, Man & Cybernetics - April 2017 - 14
Systems, Man & Cybernetics - April 2017 - 15
Systems, Man & Cybernetics - April 2017 - 16
Systems, Man & Cybernetics - April 2017 - 17
Systems, Man & Cybernetics - April 2017 - 18
Systems, Man & Cybernetics - April 2017 - 19
Systems, Man & Cybernetics - April 2017 - 20
Systems, Man & Cybernetics - April 2017 - 21
Systems, Man & Cybernetics - April 2017 - 22
Systems, Man & Cybernetics - April 2017 - 23
Systems, Man & Cybernetics - April 2017 - 24
Systems, Man & Cybernetics - April 2017 - 25
Systems, Man & Cybernetics - April 2017 - 26
Systems, Man & Cybernetics - April 2017 - 27
Systems, Man & Cybernetics - April 2017 - 28
Systems, Man & Cybernetics - April 2017 - 29
Systems, Man & Cybernetics - April 2017 - 30
Systems, Man & Cybernetics - April 2017 - 31
Systems, Man & Cybernetics - April 2017 - 32
Systems, Man & Cybernetics - April 2017 - 33
Systems, Man & Cybernetics - April 2017 - 34
Systems, Man & Cybernetics - April 2017 - 35
Systems, Man & Cybernetics - April 2017 - 36
Systems, Man & Cybernetics - April 2017 - 37
Systems, Man & Cybernetics - April 2017 - 38
Systems, Man & Cybernetics - April 2017 - 39
Systems, Man & Cybernetics - April 2017 - 40
Systems, Man & Cybernetics - April 2017 - 41
Systems, Man & Cybernetics - April 2017 - 42
Systems, Man & Cybernetics - April 2017 - 43
Systems, Man & Cybernetics - April 2017 - 44
Systems, Man & Cybernetics - April 2017 - 45
Systems, Man & Cybernetics - April 2017 - 46
Systems, Man & Cybernetics - April 2017 - 47
Systems, Man & Cybernetics - April 2017 - 48
Systems, Man & Cybernetics - April 2017 - 49
Systems, Man & Cybernetics - April 2017 - 50
Systems, Man & Cybernetics - April 2017 - 51
Systems, Man & Cybernetics - April 2017 - 52
Systems, Man & Cybernetics - April 2017 - 53
Systems, Man & Cybernetics - April 2017 - 54
Systems, Man & Cybernetics - April 2017 - 55
Systems, Man & Cybernetics - April 2017 - 56
Systems, Man & Cybernetics - April 2017 - Cover3
Systems, Man & Cybernetics - April 2017 - Cover4
https://www.nxtbook.com/nxtbooks/ieee/smc_202310
https://www.nxtbook.com/nxtbooks/ieee/smc_202307
https://www.nxtbook.com/nxtbooks/ieee/smc_202304
https://www.nxtbook.com/nxtbooks/ieee/smc_202301
https://www.nxtbook.com/nxtbooks/ieee/smc_202210
https://www.nxtbook.com/nxtbooks/ieee/smc_202207
https://www.nxtbook.com/nxtbooks/ieee/smc_202204
https://www.nxtbook.com/nxtbooks/ieee/smc_202201
https://www.nxtbook.com/nxtbooks/ieee/smc_202110
https://www.nxtbook.com/nxtbooks/ieee/smc_202107
https://www.nxtbook.com/nxtbooks/ieee/smc_202104
https://www.nxtbook.com/nxtbooks/ieee/smc_202101
https://www.nxtbook.com/nxtbooks/ieee/smc_202010
https://www.nxtbook.com/nxtbooks/ieee/smc_202007
https://www.nxtbook.com/nxtbooks/ieee/smc_202004
https://www.nxtbook.com/nxtbooks/ieee/smc_202001
https://www.nxtbook.com/nxtbooks/ieee/smc_201910
https://www.nxtbook.com/nxtbooks/ieee/smc_201907
https://www.nxtbook.com/nxtbooks/ieee/smc_201904
https://www.nxtbook.com/nxtbooks/ieee/smc_201901
https://www.nxtbook.com/nxtbooks/ieee/smc_201810
https://www.nxtbook.com/nxtbooks/ieee/smc_201807
https://www.nxtbook.com/nxtbooks/ieee/smc_201804
https://www.nxtbook.com/nxtbooks/ieee/smc_201801
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_1017
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_0717
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_0417
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_0117
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_1016
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_0716
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_0416
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_0116
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_1015
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_0715
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_0415
https://www.nxtbook.com/nxtbooks/ieee/systems_man_cybernetics_0115
https://www.nxtbookmedia.com