Toward Next-Generation Artificial Intelligence: Catalyzing the NeuroAI Revolution — part 3/3

Cleaned-text code points [28625, 41709). Bibliography omitted here; source.md includes it.

relevance.
“Engineers
don’t
study
birds
to
build
better
planes”
is
the
usual
refrain.
But
the
analogy
fails,
in
part
because
pioneers
of
aviation
did
indeed
study
birds
66,67
,
and
some
still
do
68,69
.
Moreover,
the
analogy
fails
also
at
a
more
fundamental
level:
The
goal
of
modern
aeronautical
engineering
is
not
to
achieve
“bird-level”
flight,
whereas
a
major
goal
of
AI
is
indeed
to
achieve
(or
exceed)
“human-level”
intelligence.
Just
as
computers
exceed
humans
in
many
respects,
such
as
the
ability
to
compute
prime
numbers,
so
too
do
planes
exceed
birds
in
characteristics
such
as
speed,
range
and
cargo
capacity.
But
if
the
goal
of
aeronautical
engineers
were
indeed
to
build
a
machine
with
the
“bird-level”
ability
to
fly
through
dense
forest
foliage
and
alight
gently
on
a
branch,
they
would
be
well-advised
to
pay
very
close
attention
to
how
birds
do
it.
Similarly,
if
AI
aims
to
achieve
animal-level
common-sense
sensorimotor
intelligence,
researchers
would
be
well-advised
to
learn
from
animals
and
the
solutions
they
evolved
to
behave in an unpredictable world.
Acknowledgements
This
Perspective
grew
out
of
discussions
following
the
first
conference
From
Neuroscience
to
Artificially
Intelligent
Systems
(NAISys),
held
in
CSHL
in
2020,
and
includes
many
of
the
invited
speakers
from
that
meeting.
A.Z.
would
like
to
thank
Cat
Donaldson
for
convincing
him
that
this
manuscript
would
be
worth
writing,
and
for
contributing
to
early
versions.
B.Ö.
would
like
to
acknowledge
valuable
contributions
on
the
manuscript
from
Diego
Aldorando.
The
authors
would
like
to
acknowledge
the
following
funding
sources
–
A.Z.:
Schmidt
Foundation,
Eleanor
Schwartz
Foundation,
Robert
Lourie
Foundation;
S.E.:
NIH
5U19NS104649,
5R01NS105349;
R.B.:
CIFAR,
NSERC
RGPIN-2020-05105,
RGPAS-2020-00031;
B.Ö.:
NIH
R01NS099323,
R01GM136972;
Y.B.:
CIFAR;
K.B.:
Stanford
Institute
for
Human-Centered
Artificial
Intelligence,
NSF
2223827;
A.C.:
NIH
U19NS123716;
J.D.:
Semiconductor
Research
Corporation,
DARPA,
Office
of
Naval
Research
MURI-114407,
MURI-N00014-21-1-2801,
N00014-20-1-2589,
NSF
CCF-1231216,
NSF
2124136,
Simons
SCGB
542965;
S.G.:
Simons
Foundation,
James
S.
McDonnell
Foundation,
NSF
CAREER
Award;
A.M.:
Federation
of
American
Scientists;
B.O.:
NSF
IIS-1718991;
C.S.:
NIH
1R01MH125571-01,
R01NS127122,
NSF
1922658,
Google
faculty
award;
E.S.:
Simons
Foundation,
NIH
EY022428;
S.S.:
NIH
NINDS
NS053603;
D.S.:
Simons
543049;
A.T.:
IARPA
D16PC00003,
DARPA
HR0011-18-2-0025,
NIH
R01EY026927,
R01MH109556, NSF NeuroNex DBI-1707400; D.T.: HHMI.
Competing interests
The
authors
declare
their
engagements
with
the
following
relevant
for-profit
entities
–
A.Z.:
Cajal
Neuroscience;
S.E.:
Herophilus;
R.B.:
Google
DeepMind;
B.Ö.:
Blackbird
Neuroscience;
K.B.:
Femtosense
Inc.,
Radical
Semiconductor,
Neurovigil;
C.C.:
Google
DeepMind;
S.G.:
Meta;
J.H.:
Numenta;
K.K.:
Paradromics;
T.L.:
Google
DeepMind;
A.M.:
Google
DeepMind,
Kernel;
D.S.:
Meta;
A.T.: Vathes Inc., Upload AI LLC, BioAvatar LLC.
Author contributions
A.Z.
conceived
the
project
and
wrote
the
first
draft.
A.Z.,
S.E.,
B.R.,
B.Ö.
provided
extensive
editing
to
successive drafts. All other authors provided additional guidance and edits at various stages.

References
1.
Hassabis, D., Kumaran, D., Summerfield, C. & Botvinick,
M. Neuroscience-Inspired
Artificial Intelligence.
Neuron
95
, 245–258 (2017).
2.
Macpherson, T.
et al.
Natural and Artificial Intelligence:
A brief introduction to the
interplay between AI and neuroscience research.
Neural
Networks
144
, 603–613
(2021).
3.
McCulloch, W. S. & Pitts, W. A logical calculus
of the ideas immanent in nervous
activity.
Bull. Math. Biophys.
5
, 115–133 (1943).
4.
von Neumann, J.
First draft of a report on the
EDVAC
.
http://dx.doi.org/10.5479/sil.538961.39088011475779
(1945)
doi:
10.5479/sil.538961.39088011475779
.
5.
von Neumann, J.
The computer and the brain
. (Yale
University Press, 2012).
doi:
10.12987/9780300188080
.
6.
Hubel, D. H. & Wiesel, T. N. Receptive fields,
binocular interaction and functional
architecture in the cat’s visual cortex.
The Journal
of Physiology
vol. 160 106–154
Preprint at https://doi.org/
10.1113/jphysiol.1962.sp006837
(1962).
7.
Fukushima, K. Neocognitron: a self organizing neural
network model for a
mechanism of pattern recognition unaffected by shift in position.
Biol. Cybern.
36
,
193–202 (1980).
8.
LeCun, Y. & Bengio, Y. Convolutional networks for
images, speech, and time series.

The handbook of brain theory and neural
3361
, (1995).
9.
Thorndike, E. L. Animal intelligence: An experimental
study of the associative
processes in animals. Preprint at https://doi.org/
10.1037/10780-000
(1898).
10.
Thorndike, E. L. The Law of Effect.
The American
Journal of Psychology
vol. 39
212 Preprint at https://doi.org/
10.2307/1415413
(1927).
11.
Thorndike, E. L. The fundamentals of learning.
Preprint at
https://doi.org/
10.1037/10976-000
(1932).
12.
Crow, T. J. Cortical synapses and reinforcement:
a hypothesis.
Nature
219
,
736–737 (1968).
13.
Rescorla, R. A. A theory of Pavlovian conditioning
: Variations in the effectiveness
of reinforcement and nonreinforcement.
Current research
and theory
64–99 (1972).
14.
Klopf, H. A.
Brain Function and Adaptive Systems:
A Heterostatic Theory
. (1972).
15.
Schultz, W., Dayan, P. & Montague, P. R. A neural
substrate of prediction and
reward.
Science
275
, 1593–1599 (1997).
16.
Campbell, M., Hoane, A. J. & Hsu, F.-H. Deep Blue.
Artif. Intell.
134
, 57–83 (2002).
17.
Silver, D.
et al.
Mastering the game of Go with
deep neural networks and tree
search.
Nature
529
, 484–489 (2016).
18.
Reed, S.
et al.
A Generalist Agent.
arXiv
(2022)
doi:
10.48550/arXiv.2205.06175
.
19.
Sinz, F. H., Pitkow, X., Reimer, J., Bethge, M.
& Tolias, A. S. Engineering a Less
Artificial Intelligence.
Neuron
103
, 967–979 (2019).
20.
Itti, L., Koch, C. & Niebur, E. A model of saliency-based
visual attention for rapid
scene analysis.
IEEE Trans. Pattern Anal. Mach. Intell.
20
, 1254–1259 (1998).

21.
Larochelle, H. & Hinton, G. Learning to combine foveal glimpses with a third-order
Boltzmann machine.
Advances in neural information
processing systems
23
,
(2010).
22.
Xu, K.
et al.
Show, Attend and Tell: Neural Image
Caption Generation with Visual
Attention. in
Proceedings of the 32nd International
Conference on Machine
Learning
(eds. Bach, F. & Blei, D.) vol. 37 2048–2057
(PMLR, 2015).
23.
Vaswani, A.
et al.
Attention is all you need.
Adv. Neural Inf. Process. Syst.
30
,
(2017).
24.
Moravec, H.
Mind Children: The Future of Robot
and Human Intelligence
. (Harvard
University Press, 1988).
25.
Turing, A. M. I.—COMPUTING MACHINERY AND INTELLIGENCE.
Mind
LIX
,
433–460 (1950).
26.
Brown, T.
et al.
Language models are few-shot
learners.
Adv. Neural Inf. Process.
Syst.
33
, 1877–1901 (2020).
27.
Sejnowski, T. Large Language Models and the Reverse
Turing Test.
arXiv [cs.CL]
(2022).
28.
Brooks, R. A. Intelligence without representation.
Artificial Intelligence
vol. 47
139–159 Preprint at https://doi.org/
10.1016/0004-3702(91)90053-m
(1991).
29.
Meyer, J.-A. & Wilson, S. W.
From Animals to Animats:
Proceedings of the First
International Conference on Simulation of Adaptive Behavior
. (Bradford Books,
1991).
30.
Pfeifer, R. & Scheier, C. Understanding Intelligence.
Preprint at

https://doi.org/
10.7551/mitpress/6979.001.0001
(2001).
31.
Pfeifer, R. & Bongard, J.
How the Body Shapes
the Way We Think: A New View of
Intelligence
. (MIT Press, 2006).
32.
Ortiz, C. L. Why We Need a Physically Embodied
Turing Test and What It Might
Look Like.
AI Magazine
vol. 37 55–62 Preprint at
https://doi.org/
10.1609/aimag.v37i1.2645
(2016).
33.
Merel, J., Botvinick, M. & Wayne, G. Hierarchical
motor control in mammals and
machines.
Nat. Commun.
10
, 5489 (2019).
34.
Mnih, V.
et al.
Human-level control through deep
reinforcement learning.
Nature
518
, 529–533 (2015).
35.
Huang, S., Papernot, N., Goodfellow, I., Duan,
Y. & Abbeel, P. Adversarial Attacks
on Neural Network Policies.
arXiv [cs.LG]
(2017).
36.
Zador, A. M. A critique of pure learning and what
artificial neural networks can learn
from animal brains.
Nat. Commun.
10
, 3770 (2019).
37.
Bommasani, R.
et al.
On the Opportunities and
Risks of Foundation Models.
arXiv
[cs.LG]
(2021).
38.
Elman, J. L. Learning and development in neural
networks: the importance of
starting small.
Cognition
48
, 71–99 (1993).
39.
Lake, B. M., Ullman, T. D., Tenenbaum, J. B. &
Gershman, S. J. Building machines
that learn and think like people.
Behav. Brain Sci.
40
, e253 (2017).
40.
Doya, K. & Taniguchi, T. Toward evolutionary and
developmental intelligence.
Current Opinion in Behavioral Sciences
vol. 29 91–96
Preprint at

https://doi.org/
10.1016/j.cobeha.2019.04.006
(2019).
41.
Pehlevan, C. & Chklovskii, D. B. Neuroscience-Inspired
Online Unsupervised
Learning Algorithms: Artificial Neural Networks.
IEEE
Signal Process. Mag.
36
,
88–96 (2019).
42.
Stanley, K. O., Clune, J., Lehman, J. & Miikkulainen,
R. Designing neural networks
through neuroevolution.
Nature Machine Intelligence
1
, 24–35 (2019).
43.
Gupta, A., Savarese, S., Ganguli, S. & Fei-Fei,
L. Embodied intelligence via
learning and evolution.
Nat. Commun.
12
, 5721 (2021).
44.
Stöckl, C., Lang, D. & Maass, W. Structure induces
computational function in
networks with diverse types of spiking neurons.
bioRxiv
2021.05.18.444689 (2022)
doi:
10.1101/2021.05.18.444689
.
45.
Koulakov, A., Shuvaev, S., Lachi, D. & Zador,
A. Encoding innate ability through a
genomic bottleneck.
bioRxiv
2021.03.16.435261 (2022)
doi:
10.1101/2021.03.16.435261
.
46.
Patterson, D.
et al.
Carbon Emissions and Large
Neural Network Training.
arXiv
[cs.LG]
(2021).
47.
Sokoloff, L. The metabolism of the central nervous
system in vivo.
Handbook of
physiology, section I, neurophysiology
3
, 1843–1864
(1960).
48.
Boahen, K. Dendrocentric learning for synthetic
intelligence.
Nature
612
, 43–50
(2022).
49.
Dobrunz, L. E. & Stevens, C. F. Heterogeneity
of release probability, facilitation,
and depletion at central synapses.
Neuron
18
, 995–1008
(1997).

50.
Attwell, D. & Laughlin, S. B. An energy budget for signaling in the grey matter of the
brain.
J. Cereb. Blood Flow Metab.
21
, 1133–1145 (2001).
51.
Lennie, P. The cost of cortical computation.
Curr.
Biol.
13
, 493–497 (2003).
52.
Davies, M.
et al.
Advancing neuromorphic computing
with loihi: A survey of results
and outlook.
Proc. IEEE Inst. Electr. Electron. Eng.
109
, 911–934 (2021).
53.
Cisek, P. & Hayden, B. Y. Neuroscience needs evolution.
Philos. Trans. R. Soc.
Lond. B Biol. Sci.
377
, 20200518 (2022).
54.
Mathis, A.
et al.
DeepLabCut: markerless pose
estimation of user-defined body
parts with deep learning.
Nat. Neurosci.
21
, 1281–1289
(2018).
55.
Wu, A.
et al.
Deep Graph Pose: a semi-supervised
deep graphical model for
improved animal pose tracking.
Adv. Neural Inf. Process.
Syst.
33
, 6040–6052
(2020).
56.
Marshall, J. D.
et al.
Continuous Whole-Body 3D
Kinematic Recordings across the
Rodent Behavioral Repertoire.
Neuron
109
, 420–437.e8
(2021).
57.
Pereira, T. D.
et al.
Publisher Correction: SLEAP:
A deep learning system for
multi-animal pose tracking.
Nat. Methods
19
, 628 (2022).
58.
Merel, J.
et al.
Deep neuroethology of a virtual
rodent. in
International Conference
on Learning Representations
(2020).
59.
Todorov, E., Erez, T. & Tassa, Y. MuJoCo: A physics
engine for model-based
control. in
2012 IEEE/RSJ International Conference
on Intelligent Robots and
Systems
(IEEE, 2012). doi:
10.1109/iros.2012.6386109
.
60.
Brockman, G.
et al.
OpenAI Gym. (2016) doi:
10.48550/arXiv.1606.01540
.

61.
Kitano, H., Asada, M., Kuniyoshi, Y., Noda, I. & Osawa, E. RoboCup: The Robot
World Cup Initiative. in
Proceedings of the first
international conference on
Autonomous agents
340–347 (Association for Computing
Machinery, 1997).
62.
Bell, R. M. & Koren, Y. Lessons from the Netflix
prize challenge.
ACM SIGKDD
Explorations Newsletter
vol. 9 75–79 Preprint at
https://doi.org/
10.1145/1345448.1345465
(2007).
63.
Doya, K., Ema, A., Kitano, H., Sakagami, M. &
Russell, S. Social impact and
governance of AI and neurotechnologies.
Neural Netw.
152
, 542–554 (2022).
64.
Liu, S.
et al.
From Motor Control to Team Play
in Simulated Humanoid Football.
arXiv [cs.AI]
(2021).
65.
MICrONS Consortium
et al.
Functional connectomics
spanning multiple areas of
mouse visual cortex.
bioRxiv
2021.07.28.454025 (2021)
doi:
10.1101/2021.07.28.454025
.
66.
Lilienthal, O.
Birdflight as the Basis of Aviation:
A Contribution Towards a System of
Aviation, Compiled from the Results of Numerous Experiments Made by O. and G.
Lilienthal
. (Longmans, Green, 1911).
67.
Culick, F. What the Wright Brothers did and did
not understand about flight
mechanics - In modern terms. in
37th Joint Propulsion
Conference and Exhibit
(American Institute of Aeronautics and Astronautics, 2001).
68.
Shyy, W., Lian, Y., Tang, J., Viieru, D. & Liu,
H.
Aerodynamics of low Reynolds
number flyers
. (2008).
69.
Akos, Z., Nagy, M., Leven, S. & Vicsek, T. Thermal
soaring flight of birds and

unmanned aerial vehicles.
Bioinspir. Biomim.
5
, 045003 (2010).