Julian Francis Miller, 1955–2022
Susan Stepney
University of York, 英国
计算机科学系
Alan Dorin
Monash University, 澳大利亚
Department of Data Science and AI
我
D
哦
w
n
哦
A
d
e
d
F
r
哦
米
H
t
t
p
:
/
/
d
我
r
e
C
t
.
米
我
t
.
e
d
你
A
r
t
我
/
/
我
A
r
t
我
C
e
–
p
d
F
/
/
/
/
2
8
1
1
5
4
2
0
2
9
1
9
8
A
r
t
我
/
_
A
_
0
0
3
7
1
p
d
.
F
乙
y
G
你
e
s
t
t
哦
n
0
8
S
e
p
e
米
乙
e
r
2
0
2
3
Julian Francis Miller1
It is with great sadness that we report the death of our colleague and friend, Julian Miller.
Julian’s work is well known throughout the Artificial Life community: His Cartesian genetic pro-
gramming (CGP) and in materio computing are foundational concepts. He also made contributions
in morphological computing and neurocomputing, all based on his fascination with evolution as a
means of attacking and solving problems. Like many in the ALife community, he had an interdis-
ciplinary career, commencing with a first degree in Physics and a PhD in Mathematics, 其次是
research in Natural Computing and material computing at the universities of Napier, Birmingham,
and York in the UK.
Julian invented CGP (磨坊主, 1999), a way of encoding graph programs (functional nodes con-
nected by edges) in a string of integers, allowing the string to be evolved in the standard way, 和
the graph (located on a Cartesian grid, hence its name) produced as the result of a genotype to
phenotype mapping. From this simple beginning, Julian and his students continued to develop the
方法, and other researchers joined in. 十年后, the field had grown significantly, 和
many researchers both using CGP in their own work and extending the original concept. 的确,
the field had grown enough that Julian could edit an entire book on the topic (磨坊主, 2011).
1 Photograph © 2006 Gabriele Miller; used with permission.
© 2022 Massachusetts Institute of Technology Artificial Life 28: 154–156 (2022) https://doi.org/10.1162/artl_a_00371
Stepney and Dorin
Julian Francis Miller, 1955–2022
Ten years later still, the field shows no signs of abating, and Julian wrote a 40-page review for
Genetic Programming and Evolvable Machines on CGP’s status, its many variants, and its future prospects
(磨坊主, 2020).
Julian was also a pioneer in the field of in materio computing (磨坊主 & 唐宁, 2002), which ex-
ploits the physical properties of unconventional materials, such as liquid crystals (Harding & 磨坊主,
2004) and carbon nanotubes (Miller et al., 2014), to perform computation intrinsically, in what he
dubbed a “Field Programmable Matter Array.” His original work used evolutionary algorithms di-
rectly to configure the materials. 之后, he also used Reservoir Computing as a more abstract model
for getting these materials to compute (Dale et al., 2017). This is another field with explosive growth,
so much so that some authors have even published on the name of the domain itself (Ricciardi &
米兰, 2022). Julian was there from the start, contributing his insights and ideas throughout.
CGP and in materio computing may be what Julian is best known for, but these contributions
were embedded in a deeper research program of understanding development as a fundamental com-
ponent of evolving embodied computation. From growing a self-repairing “French-flag” organism
(磨坊主, 2004), to assembling complex structures through Artificial Chemistries (Faulconbridge et al.,
2011), to the idea of the “software garden” (磨坊主, 2018), Julian felt that both growth and evolution
are essential concepts in complex systems.
His Festschrift Inspired by Nature (Stepney & Adamatzky, 2018) was a (slightly late) 60th birth-
day present from his many academic colleagues. It includes chapters contributed by a wide range
of authors who have built on and been inspired by his many research interests. The text covers
evolution and hardware, CGP applications, 化学, and development. Julian retired in 2016, 但
he did not stop his research. He used the freedom from the quotidian constraints of an academic
job to pursue a new interest. He was bringing together his discoveries in evolution, 发展,
网络, and computation to develop a new neural model to evolve programs that build, or grow,
神经网络. His most recent publication on that topic has only just appeared (磨坊主, 2022).
Julian’s retirement also allowed him to spend time with his recently acquired beloved new fam-
伊利. His wife Gabi remembers him thus: “He was a loving and generous-hearted husband, a wise
step-father to my three grown adults and much loved Grandpa to our four grand-children. Jules will
be sadly missed, but also lovingly remembered by all whose life he touched.” Many further tributes
to Julian from his colleagues can be found in the latest SIGEVO newsletter (Ochoa, 2022).
参考
戴尔, M。, 磨坊主, J. F。, & Stepney, S. (2017). Reservoir computing as a model for in-materio computing.
在一个. Adamatzky (埃德。), Advances in Unconventional Computing (PP. 533–571). 施普林格. https://doi.org/10
.1007/978-3-319-33924-5_22
Faulconbridge, A。, Stepney, S。, 磨坊主, J. F。, & Caves, L. S. D. (2011). RBN-World: A subsymbolic artificial
化学. ECAL 2009, 5777, 377–384. https://doi.org/10.1007/978-3-642-21283-3_47
Harding, S。, & 磨坊主, J. F. (2004). Evolution in materio: Initial experiments with liquid crystal. In Proceedings,
2004 NASA/DoD Conference on Evolvable Hardware. https://doi.org/10.1109/EH.2004.1310844
磨坊主, J. F. (1999). An empirical study of the efficiency of learning boolean functions using a Cartesian
Genetic Programming approach. In Proceedings of the 1st Annual Conference on Genetic and Evolutionary
Computation—Volume 2, 1135–1142.
磨坊主, J. F. (2004). Evolving a self-repairing, self-regulating, french flag organism. In GECCO 2004, 129–139.
https://doi.org/10.1007/978-3-540-24854-5_12
磨坊主, J. F. (埃德。). (2011). Cartesian genetic programming. 施普林格. https://doi.org/10.1007/978-3-642-17310-3
磨坊主, J. F. (2018). The software garden. 在R中. Walsh & S. Stepney (编辑。), Narrating complexity (PP. 201–212).
施普林格. https://doi.org/10.1007/978-3-319-64714-2_15
磨坊主, J. F. (2020). Cartesian genetic programming: Its status and future. Genetic Programming and Evolvable
Machines, 21(1), 129–168. https://doi.org/10.1007/s10710-019-09360-6
磨坊主, J. F. (2022). IMPROBED: Multiple problem-solving brain via evolved developmental programs.
Artificial Life, 27(3–4), 300–335. https://doi.org/10.1162/artl_a_00346
Artificial Life Volume 28, 数字 1
155
我
D
哦
w
n
哦
A
d
e
d
F
r
哦
米
H
t
t
p
:
/
/
d
我
r
e
C
t
.
米
我
t
.
e
d
你
A
r
t
我
/
/
我
A
r
t
我
C
e
–
p
d
F
/
/
/
/
2
8
1
1
5
4
2
0
2
9
1
9
8
A
r
t
我
/
_
A
_
0
0
3
7
1
p
d
.
F
乙
y
G
你
e
s
t
t
哦
n
0
8
S
e
p
e
米
乙
e
r
2
0
2
3
Stepney and Dorin
Julian Francis Miller, 1955–2022
磨坊主, J. F。, & 唐宁, K. (2002). Evolution in materio: Looking beyond the silicon box. In Proceedings, 2002
NASA/DoD Conference on Evolvable Hardware, 167–176. https://doi.org/10.1109/EH.2002.1029882
磨坊主, J. F。, Harding, S. L。, & Tufte, G. (2014). Evolution-in-materio: Evolving computation in materials.
Evolutionary Intelligence, 7(1), 49–67. https://doi.org/10.1007/s12065-014-0106-6
Ochoa, G. (埃德。). (2022). Tributes to Julian F. 磨坊主 (1955–2022). SIGEVOlution: Newsletter of the ACM Special
Interest Group on Genetic and Evolutionary Computation, 15(1). https://evolution.sigevo.org/issues/HTML
/sigevolution-15-1/home.html#h.6uzth8kptc5x, https://doi.org/10.1145/3532942.3532943
Ricciardi, C。, & 米兰, G. (2022). In materia should be used instead of in materio. Frontiers in Nanotechnology, 4.
https://doi.org/10.3389/fnano.2022.850561
Stepney, S。, & Adamatzky, A. (编辑。). (2018). Inspired by nature: Essays presented to Julian F. Miller on the occasion of
his 60th birthday. 施普林格.
我
D
哦
w
n
哦
A
d
e
d
F
r
哦
米
H
t
t
p
:
/
/
d
我
r
e
C
t
.
米
我
t
.
e
d
你
A
r
t
我
/
/
我
A
r
t
我
C
e
–
p
d
F
/
/
/
/
2
8
1
1
5
4
2
0
2
9
1
9
8
A
r
t
我
/
_
A
_
0
0
3
7
1
p
d
.
F
乙
y
G
你
e
s
t
t
哦
n
0
8
S
e
p
e
米
乙
e
r
2
0
2
3
156
Artificial Life Volume 28, 数字 1