IEEE Systems, Man and Cybernetics Magazine - April 2018 - 7

sometimes even humans. Rémi Coulom, a freelance developer of Go programs, notes, "Online games are usually
played at a faster pace, which favors the computer over
humans," and, still, he expects a strong correlation in performance in serious tournament games [1]. This is why Go
games were played on site rather than just on the Internet
at the special event "Human and Smart Machine Co-Learning" [11], which was held during the IEEE International
Conference on Systems, Man, and Cybernetics (SMC) on
5 October 2017 in Banff, Canada.
The purpose of these activities at the IEEE SMC 2017
were: 1) to integrate the open-source Facebook artificial
intelligence (AI) research (FAIR) DarkForest (DF) program [2] with the item response theory [8] of the National
University of Tainan (NUTN), Taiwan, resulting in a new,
open-learning system, i.e., Dynamic DF (DDF) [3]; 2) to
integrate DDF Go with FUJISOFT Robot (led by Kubota
Lab, Tokyo Metropolitan University, Japan), i.e., the robotic DDF Go system; and 3) to invite professional Go players
to attend the event to play Go games on site with a smart
machine. Chun-Hsun Chou (9P, Taiwan), Ping-Chiang
Chou (6P, Taiwan), and Kai-Hsin Chang (5P, Taiwan) were
invited to play Go games with DeepZenGo (Japan). Alternatively, Lu-An Lin (6D, Taiwan), Daisuke Horie (4D,
Japan), and Shuji Takemura (1D, Japan) played games
with the DDF (Taiwan) embedded FAIR DF Open Go AI
engine [2]. [A Go player's skill level is ranked by a letter
and number. According to [6], Dan (D) is the higher tier
for amateur players, where a larger number stands for
stronger playing skill. Professional Go players are indicated
with the letter P.] In addition, the collaborative research
team from National Chiao Tung University (NCTU),
NUTN, the University of California San Diego, and the
National Center for High-Performance Computing
(NCHC) jointly integrated the brain-computer interface
(BCI) with the current DDF (called BCI-DDF) Go system,
which was demonstrated to attract more scholars to the
brain-machine interaction area at the IEEE SMC conference and to encourage SMC Society membership.
Past Events 2008-2017
In 2017, for the first time, the
"Human and Smart Machines CoLearning" event was held at the
IEEE SMC. However, events where
humans play against computer Go
programs have been established
for almost a decade [6], [7]. Figure 1
shows the human versus computer Go competitions from 2008 to
2017 [12], which were funded by
the IEEE Computational Intelligence Society, the IEEE SMC, the
Taiwanese government, NUTN,

and the Taiwanese
Association for Artificial Intelligence. In
1998, the handicap for
t he hu man versus computer 19 # 19 game was 29
stones [6]. However, from 2008 to
2017, the power of computer Go programs increased from a seven-stone handicap to a zerostone handicap against top professional Go players.
Additionally, in 2016 and 2017, Google successfully combined deep-learning technologies and computer hardware
with a Monte Carlo tree to defeat many top professional Go
players without handicaps [4], [5].

BCI-DDF Go System
At the IEEE SMC 2017 special event, we combined the theory of deep learning with the technology of BCI [9], [10] to
demonstrate Go gameplay. Brainwave technology has been
developing for a long time; however, applying the technology
to play Go at an IEEE conference was a first. The world's latest mobile and wireless electroencephalogram (EEG) system is fully utilized in the innovation of the developed
BCI-DDF Go system. The wireless system, developed by the
research team from the Brain Research Center at NCTU, is
designed to extract the Go player's brainwaves when he or
she competes with the DDF Go system directly. Figure 2
shows the two-mode (competitive learning and predictive
learning modes) scenario used at the "Human and Smart
Machine Co-Learning" event; it also displays the invited Go
players, computer Go programs, robot Palro, and the developed BCI-DDF Go system.
Figure 3 includes the BCI-DDF Go system diagram
used by Lu-An Lin (6D) while playing Go with DDF
hands-free. The robot, Palro, reported the next moves
as suggested by the DDF. We adopted the steady-state
visually evoked potential technology to collect the brain
signals from the visual cortex [occipital 1 (O1) and
occipital 2 (O2) channels] and performed the real-time
signal processing in the cloud
server. Five pilot players tested
the developed BCI-DDF Go sysWhen it comes to
tem, and, prior to this special
event, it reached approximately
smart machines,
90% accuracy on a five-class clasit is not just about
sification task. The demonstramethodologies; we
tion of the BCI-DDF Go system is
expressive of the breakthrough
also need to consider
in human brain interaction with
systems, cybernetics,
AI. Participants wore a wireless
EEG headset and were instructed
and sometimes
to gaze at the coded visual stimueven humans.
lus on the screen The BCI-DDF
GO system continuously decoded
Ap ri l 2018

IEEE SyStEmS, man, & CybErnEtICS magazInE

7



Table of Contents for the Digital Edition of IEEE Systems, Man and Cybernetics Magazine - April 2018

Contents
IEEE Systems, Man and Cybernetics Magazine - April 2018 - Cover1
IEEE Systems, Man and Cybernetics Magazine - April 2018 - Cover2
IEEE Systems, Man and Cybernetics Magazine - April 2018 - Contents
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 2
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 3
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 4
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 5
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 6
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 7
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 8
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 9
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 10
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 11
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 12
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 13
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 14
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 15
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 16
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 17
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 18
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 19
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 20
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 21
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 22
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 23
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 24
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 25
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 26
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 27
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 28
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 29
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 30
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 31
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 32
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 33
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 34
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 35
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 36
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 37
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 38
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 39
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 40
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 41
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 42
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 43
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 44
IEEE Systems, Man and Cybernetics Magazine - April 2018 - Cover3
IEEE Systems, Man and Cybernetics Magazine - April 2018 - 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