July 16, 2004—create something
that endures through time and uncov-
ers fundamental principles of com-
puting at the forefront of knowledge.
And make it available in the service of
making the world work better.
“That’s what motivates me personally
Along with TrueNorth, IBM developed
an end-to-end ecosystem for developing applications on these brain-inspired chips that includes a simulator,
a programming language, sample
algorithms/applications, a library and a
It currently sits in the hands of 430
researchers at more than 40 institutions
worldwide, but—ever the collaborator—
Modha is looking to expand the user
base even further in the coming year.
Chip-wise, Modha said the next
steps are very clear. In the next five
to 10 years, he and his team want to
create a brain-in-a-box—a supercomputer the size of a shoebox with 10
billion neurons and one hundred trillion
synapses that consumes less than 1
kilowatt of power.
“I have a palpable sense that we are
at a turning point in the history of computing,” Modha concluded. “The technological and practical possibilities are
immense and could touch every sphere
of science, technology, business,
government and society. I am optimistic that the enduring value of our work
will be the inspiration of a completely
different way of thinking about computing. We are not there yet. TrueNorth is
a direction and not a destination. The
end goal is building intelligent business
machines that enable a cognitive planet, while transforming industries.”
- Michelle Taylor, Editor-in-Chief,
operated in parallel. Unlike von Neumann architecture, TrueNorth’s computation, memory and communication
are integrated, which results in a cool
operating environment (allowing the
chips to be stacked) and low power
operation. Individual cores can fail and
yet, like the brain, the architecture can
still function. Cores on the same chip
communicate with one another via an
on-chip event-driven network. Chips
communicate via an inter-chip interface
leading to seamless scalability.
This version of TrueNorth—literally a
supercomputer the size of a postage
stamp with the power of a hearing aid
battery—debuted in 2014.
Success through collaboration
Collaboration—both internally and
externally—was absolutely vital to the
success of TrueNorth.
“If it takes a village to raise a child, it
takes a community to bring something
like this from a doodle on the back of a
napkin to reality,” said Modha.
Externally, IBM and Modha collaborated with more than 200 universities,
government labs, companies and
non-profits—Lawrence Livermore National Laboratory, Samsung, Stanford
University, Cornell University, Columbia
University—the list goes on.
Internally, Modha’s group worked
with multiple labs within IBM, including
the semiconductor lab, which played a
vital role in designing emerging material
Additionally, Modha said his immediate team was deeply collaborative,
and very flat. There was no established
hierarchy in order to emphasize an
environment in which all members’
creativity was considered. No matter
how young, how inexperienced, how
new to the project, or how different, all
prospectives were considered before
the team collectively settled on a unified direction.
In August 2015, Modha held a three-
week “TrueNorth Bootcamp,” where he
began to unveil and teach the ecosys-
tem he developed. Representatives
from more than 40 universities, gov-
“This was key
because what we devel-
oped is not a point technology,” Modha
said. “We developed a substrate, a
platform that is going to revolutionize
computing from Io T, smartphones,
mobile tech, embedded computing,
robotics, cars, cameras, imaging ma-
chines to cloud and supercomputing.
This isn’t about one application or one
algorithm or one architecture, it’s really
about a pervasive platform that could
truly touch on all aspects of computing.
It’s bringing to bear the creativity of
the community here to truly push the
Another aspect that was vital to the
project—and will remain so as research
continues—is long-term motivation.
This research has gone on for more
than a decade, and endured in an R&D
climate that expects short-term gains in
a long-term field.
From an organizational perspective,
the environment at IBM is designed to
“enable, nurture and protect long-term
efforts” to make the world a better
place, according to Modha.
From a team perspective Modha said
he has come to the conclusion that the
second law of thermodynamics—the
entropy of the universe tends to a maximum—is evil.
“The key to managing a project over
the long-term is two-fold—know where
we are headed so one can continue
to construct complexity in the desired
direction, and know where we are not
headed so as to prevent the second
law of thermodynamics from creeping
in and creating heat and entropy that
does not further purposeful motion.”
The third perspective is personal mo-
tivation. And for Modha, it goes all the
way back to that decision he made on
This image was created
by Modha and his team
as they mapped out 383
regions of the macabre
monkey brain. Photo: