10/2018
VOL. 61 NO. 10
Practice
36 The Mythos of Model Interpretability
In machine learning,
the concept of interpretability is
both important and slippery.
By Zachary C. Lipton
44 The Secret Formula for Choosing
the Right Next Role
The best careers are not defined
by titles or résumé bullet points.
By Kate Matsudaira
47 Mind Your State for
Your State of Mind
The interactions between
storage and applications
can be complex and subtle.
By Pat Helland
Articles’ development led by
queue.acm.org
(
L
)
I
M
A
G
E
B
Y
E
S
B
P
R
O
F
E
S
S
I
O
N
A
L
;
(
C
)
I
L
L
U
S
T
R
A
T
I
O
N
B
Y
H
U
G
H
S
Y
M
E
;
(
R
)
P
H
O
T
O
B
Y
G
E
N
C
H
O
P
E
T
K
O
V
Contributed Articles
56 Human-Level Intelligence
or Animal-Like Abilities?
What just happened in
artificial intelligence and how
it is being misunderstood.
By Adnan Darwiche
68 Formally Verified Software
in the Real World
Verified software secures
the Unmanned Little Bird
autonomous helicopter against
mid-flight cyber attacks.
By Gerwin Klein, June Andronick,
Matthew Fernandez, Ihor Kuz,
Toby Murray, and Gernot Heiser
78 The Productivity Paradox in
Health Information Technology
New York State healthcare providers
increased their use of the technology
but delivered only mixed results for
their patients.
By Quang “Neo” Bui, Sean Hansen,
Manlu Liu, and Qiang (John) Tu
Watch the author discuss
his work in the exclusive
Communications video.
https://cacm.acm.org/
videos/human-level-intelligence-or-animal-like-abilities
Review Articles
86 Computing within Limits
The future of computing research
relies on addressing an array
of limitations on a planetary scale.
By Bonnie Nardi, Bill Tomlinson,
Donald J. Patterson, Jay Chen,
Daniel Pargman, Barath Raghavan,
and Birgit Penzenstadler
Research Highlights
95 Technical Perspective
A Control Theorist’s View on Reactive
Control for Autonomous Drones
By John Baillieul
96 Fundamental Concepts of Reactive
Control for Autonomous Drones
By Luca Mottola and Kamin Whitehouse
105 Technical Perspective
The Future of MPI
By Marc Snir
106 Enabling Highly Scalable Remote
Memory Access Programming
with MPI-3 One Sided
By Robert Gerstenberger,
Maciej Besta, and Torsten Hoefler
About the Cover:
This month’s cover was
inspired by a Judea Pearl
quote that contends the
vision system of an eagle
outperforms anything
created in the lab, yet
the eagle cannot build a
telescope or microscope.
Adnan Darwiche uses
this quote as a jumping-off
point to argue what AI is
and is not doing today
(p. 56). Cover illustration
by Hugh Syme.
44 56 86