Instrumented Interconnecteds Intelligent

Principal Investigator—SyNAPSE;  Senior Manager—Cognitive Computing

Dharmendra S. Modha, Principal Investigator, SyNAPSE; Senior Manager, Cognitive Computing; IBM

By Dharmendra S. Modha

Sixty years ago, in the face of tremendous skepticism, IBM engineer John Backus set out to radically change the economics of scientific computing on the IBM 704 by making programming much cheaper, faster, and reliable.  The language that he and his colleagues developed—FORTRAN—became the first widely used high-level programming language.  It laid the groundwork for the software industry as we know it and the waves of transformation that computing has brought to industry, science, government and society.  The importance of FORTRAN is hard to overestimate as demonstrated by O’Reilly’s poster on “The History of Programming Languages.”

Today, we’re at another turning point in the history of information technology.  The era that Backus and his contemporaries helped create, the programmable computing era, is being superseded by the era of cognitive computing.  Increasingly, computers will gather huge quantities of data, reason over the data, and learn from their interactions with information and people.  These new capabilities will help us penetrate complexity and make better decisions about everything from how to manage cities to how to solve confounding business problems.

But, in order for cognitive computing to take hold, scientists will have to re-architect nearly every aspect of computing spanning—silicon, systems, storage, and software.  In the process, a new programming paradigm must be developed, corresponding to the one underlying FORTRAN.  I’m proud to say that the SyNAPSE team at IBM, with help from university scientists, has taken a first step toward inventing just such a new programming model. We call our concept corelet programming.

If you want to learn more about the era of cognitive computing, download a free chapter of Smart Machines, a book by IBM Research Director John E. Kelly III, at the Web site of Columbia University Press, http://cup.columbia.edu/static/cognitive.

We are developing this technology for the SyNAPSE project, a multi-year initiative funded in part by the U.S. Defense Advanced Research Projects Agency.  The goal is to create cognitive processor chips and systems, inspired by the function, low-power, and compact size of the mammal brain, which can enable a host of next-generation cognitive software applications. See examples of potential cognitive apps in the video.

YouTube Preview Image

The creation of FORTRAN was hugely ambitious; SyNAPSE is a hugely ambitious project in its own right.  We have envisioned an entirely new computing architecture—a network of neurosynaptic processor cores, which, like the brain, is modular, parallel, distributed, fault-tolerant, event-driven, and scalable. Earlier, we demonstrated individual neurosynaptic processor cores, the key building blocks, using IBM’s silicon technology. In addition, we have simulated a network of billions of such neurosynaptic processor cores—reaching the brain’s scale of one hundred trillion synapses—on IBM’s largest supercomputer, Sequoia, at Lawrence Livermore National Lab.

Our architecture is radically different from today’s prevalent computing architecture.  Trying to adapt existing programming languages to it is like trying to force a square peg in a round hole. A new approach to programming is needed.

Enter the corelet model.  It’s a high-level description of a software program that is based on re-usable building blocks of code—the corelets. Each corelet represents a method for getting something done using the combination of computation (neuron), memory (synapses), and communication (axons) on individual neurosynaptic processor cores along with inter-core connectivity. Each corelet hides or encapsulates all details except external inputs and outputs.

Corelets are like LEGO blocks.  Small individual corelets handle simple functions. When combined, they create new, larger corelets that aggregate functions and add new ones while hiding the underlying component corelets.  In this way, the programmer can write large and complex programs using existing building blocks.  Using this model and the programming language for executing on it, it will be possible for programmers to produce a large quantity of efficient code with relatively little effort and for people who are not programming experts to create sophisticated cognitive applications. That’s much the same effect that FORTRAN had on the computing world in its early days.

Along with the new architecture and the new programming model, we’ve created significant software and hardware technologies that represent a vertically integrated technology ecosystem—a new foundation for a new era of computing.

John Backus is rightly celebrated for his tremendous accomplishments at the dawn of the programmable computing era. Yet as John’s career proceeded, he came to recognize some of the limitations of the computer architecture laid out by mathematician John von Neumann in the 1940s—upon which his programming model and, indeed, all of modern computing, is based.  In the lecture John delivered when he received the prestigious Turing Prize in 1977, he coined the term “the von Neumann bottleneck” to describe the inefficiencies of that architecture.  In 1979, he wrote, “I now regard all conventional languages (FORTRANs, ALGOLs, their successors and derivatives) as increasingly complex elaborations of the style of programming dictated by the von Neumann computer. … It is unfortunate because their long-standing familiarity will make it hard for us to understand and adopt new programming styles which one day will offer far greater intellectual and computational power”. (John died in 2007, at age 82.)

Today, a worldwide, interdisciplinary effort has begun to invent a new, non-von Neumann architecture for computing that complements today’s computers.  This will be essential for the emergence of cognitive computing.  My team’s architecture and corelet programming model are important contributions to this effort. Ultimately, the march of time will decide whether our inventions will have the same kind of catalytic impact on the new era of computing that the work of John Backus and his team had on the last one.  But, the best way to predict the future is to create it.

https://dl.dropboxusercontent.com/u/91714474/Press/08082013/Pictures/Almaden%20Team%20Outside.jpg Caption:  Front row, left-to-right: Davis Barch, Pallab Datta, Sue Gilson, David Peyton, Kumar Appuswamy, Brian Taba, Norm Pass, Wendy Belluomini, Nitin Parekh;  Middle row, left-to right: Ben Shaw, Andrew Cassidy, Paul A. Merolla, Jeff Kusnitz, Arnon Amir, Dharmendra S. Modha, David J. Berg, Alexander Andreopoulos;  Back row, left-to-right: Chris Hanson, Steven K. Esser, Emmett McQuinn, Rodrigo Alvarez-Icaza, Bill Risk, Myron Flickner, John Arthur, Bryan Jackson.  For more photos of the IBM SyNAPSE team around the world, see my blog.

Photo: Hita Bambhinia-Modha

Front row, left-to-right: Davis Barch, Pallab Datta, Sue Gilson, David Peyton, Kumar Appuswamy, Brian Taba, Norm Pass, Wendy Belluomini, Nitin Parekh; Middle row, left-to right: Ben Shaw, Andrew Cassidy, Paul A. Merolla, Jeff Kusnitz, Arnon Amir, Dharmendra S. Modha, David J. Berg, Alexander Andreopoulos; Back row, left-to-right: Chris Hanson, Steven K. Esser, Emmett McQuinn, Rodrigo Alvarez-Icaza, Bill Risk, Myron Flickner, John Arthur, Bryan Jackson.  For more photos of the IBM SyNAPSE team around the world, see my blog.

________________________________________________________________ 

Follow IBM Smarter Planet on Google+

Bookmark and Share

Previous post

Next post

25 Comments
 
April 14, 2014
9:40 am

Hi, the whole thing is going sound here and ofcourse every one is sharing information,
that’s actually good, keep up writing.


Posted by: about running for weight loss training
 
April 9, 2014
10:15 pm

Using this model and the programming language for executing on it,


Posted by: Casquette OBEY
 
March 12, 2014
12:04 am

Your way of describing the whole thing in this paragraph is actually nice, all
be able to simply understand it, Thanks a lot.


Posted by: windows 8 loader v1.7.9 windows 8 activation for all versions
 
January 9, 2014
5:42 am

I got this web site from my buddy who informed me about this website and now this time I am visiting this site and reading very informative content at
this place.


Posted by: techhaven.de
 
January 2, 2014
12:56 am

those people’s designer sunglasses, she is depend, secure her sight from the acttacked.
Don’t forget to check out the best free i – Phone games too.
I can only imagine what the outside world thinks of America
and its racist folly.


Posted by: Jamey
 
December 29, 2013
2:15 pm

Not new and not “news”!!! What Hopfield and student Sejnowski never realized nor gave credit for is as follows: Artificial neural-networks(ANN) patterned on biological neural networks(BNN) artificial-intelligence(ANN) were alive and well long before 1980 when physicist Edward Siegel [consulting with Richard Feynman(Caltech) for ANN AI pioneer Charles Rosen(Machine-Intelligence) & Irwin Wunderman(H.P.) & Vesco Marinov & Adolph Smith(Exxon Enterprises/A.I.) discovered trendy much-hyped "quantum-computing" by two-steps: (1) "EUREKA": realization that ANNs by-rote on-node switching sigmoid-function 1/[1 + e^(E/T)] ~ 1/[1 + e^(hw/kT)] ~ 1/[+ 1 + e^(E/T)] ~ 1/[ + 1 + e^(hw/kT)] is Fermi-Dirac quantum-statistics 1/[1 + e^ (E/ T)] ~ 1/[1 + e^(hw/kT)] ~ 1/[+ 1 + e^(E/T)] ~ 1/[ + 1 + e^(hw/kT)] = 1/[e^(hw/kT) + 1] dominated by Pauli exclusion-principle forcing non-optimal local-minima(example: periodic-table’s chemical-elements) forcing slow memory-costly computational-complexity Boltzmann-machine plus simulated-annealing, but permitting from non-optimal local-minima to optimal global-minimum quantum-tunneling!!! (2) “SHAZAM”: quantum-statistics “supersymmetry”- transmutation from Fermi-Dirac to Bose-Einstein 1/[+ 1/[e^(hw/kT) + 1] —> 1/[e^(hw/kT) - 1] ~ 1/f power-spectrum, with no local-minima and permitting Bose-Einstein condensation( BEC) via a noise-induced phase-transition (NIT). Frohlich biological BEC & BNN 1/f-”noise”~”generalized-susceptibility” power-spectrum concurred!!! Siegel’s work[IBM Conference on Computers & Mathematis,Stanford(1986); Symposium on Fractals, MRS Fall Meeting, Boston(1989)=five seminal-papers!!!] was used without any attribution whatsoever as/by “Page-Brin” PageRank[R. Belew, Finding Out About, Cambridge(2000)]Google first search-engine!!! Siegel empirically rediscovered Aristotle’s”square-of-opposition” in physics and mathematics, which three-dimensionally tic-tac-toe diagrams synonyms(functors) versus antonyms (morphisms) versus analogy/metaphor. Amazingly neuroimager Jan Wedeen has recently clinically discovered just such a three-dimensional network of neurons which dominates human brain thinking. Siegel “FUZZYICS=CATEGORYICS=PRAGMATYICS”/ Category-Semantics Cognition for physics/mathematics is a purposely-simple variant of Altshuler-Tsurakov-Lewis “TRIZ”(Russian acronym: “Method of Inventive Problem-Solving”) embodied in softwares Invention-Machine(Boston) and Ideation(Michigan)for engineers inventing optimality!
Dr. Edward Siegel
“physical-mathematicist”
CATEGORYSEMANTICS@GMAIL.COM
(206) 659-0235


Posted by: EDWARD SIEGEL
 
December 23, 2013
3:42 am

Do you have a spam issue on this website; I also
am a blogger, and I was wondering your situation; many of us
have created some nice methods and we are looking to swap techniques with other folks, be sure to shoot me an email if interested.


Posted by: Chicken Coup Designs
 
December 17, 2013
4:04 am

Hi my friend! I want to say that this article is amazing, great written
and come with almost all vital infos. I’d like to peer more posts like
this .


Posted by: google.com
 
December 10, 2013
9:10 pm

whatever and however we still have to appreciate the work of John Backus, because he is happy or not tim (John Backus) has been laying the foundation for the development of programming technologies


Posted by: AGEN TAS TUPPERWARE
 
December 7, 2013
8:35 am

Hi there to all, the contents present at this web page are actually remarkable for people knowledge, well, keep
up the nice work fellows.


Posted by: weight loss tips
 
December 6, 2013
7:49 pm

But as I say that, I rsalize the suppressed palette of the place did affect me
emotionally. I remember it was gray; was stained brown from the traffic and thee skky dark.
When thgeir fruit was in seazson the farmers would be doubly busy.


Posted by: windows 7 3d desktop themes
 
November 29, 2013
9:46 pm

good.. :“I now regard all conventional languages (FORTRANs, ALGOLs, their successors and derivatives) as increasingly complex elaborations of the style of programming dictated by the von Neumann computer. … It is unfortunate because their long-standing familiarity will make it hard for us to understand and adopt new programming styles which one day will offer far greater intellectual and computational power”. (John died in 2007, at age 82.)


Posted by: ADI NUGRAHA
 
November 29, 2013
9:41 pm

This will also pave the way for thought signal transmission.


Posted by: Yudhi
 
November 29, 2013
9:39 pm

this is technology for the SyNAPSE project


Posted by: Yudhi
 
November 22, 2013
6:59 am

The computers moved into homes with desktop computers.
These are just number of of the numerous issues we have with
regard to this new technologies. Like looking for other supplies, you
can verify out the details about the item or providers presented by the small business.


Posted by: laptops review
 
October 30, 2013
9:21 am

When I initially left a comment I seem to have clicked on the -Notify me when new comments
are added- checkbox and from now on whenever a comment is added I recieve 4
emails with the same comment. Perhaps there is an
easy method you can remove me from that service?
Many thanks!


Posted by: Marlys
 
October 18, 2013
4:26 pm

I will immediately grab your rss as I can’t in finding
your e-mail subscription link or e-newsletter service. Do you’ve any?
Please allow me know in order that I may subscribe.
Thanks.


Posted by: Atrie krediti
 
September 4, 2013
8:55 am

Further research results can be generated this way:

cat GangOf4Book | sed ‘s/object/corelet/g’


Posted by: Konrad Zuse
 
August 15, 2013
3:34 pm

Kursweil thinks computers will be trillions times our intelligence by 2030.how when still not even the intelligence of a 4 year old with no common sense


Posted by: francis short jr
 
August 13, 2013
8:16 am

computation (neuron), memory (synapses), and communication (axons) sounds like MVC – model (synapses), view (axons), control (neuron).

HP


Posted by: Heinz Peter Hippenstiel
 
August 13, 2013
3:04 am

Interesting O’Reilly’s poster missed out several key IBM programming languages


Posted by: Alan
 
August 10, 2013
3:32 am

The idea is excellent but my question is how it will fit in the market and use with the quantum computing and computers.
Will quantum computers be using this cognitive hardware architecture or how do you perceive it.


Posted by: Sunil Mandhan
 
August 9, 2013
2:37 pm

Since Python actually has better MATLAB-like modules than MATLAB itself, it should have been built on Python, a widely-used and powerful language that already has plenty of very good programmers who know it and who would be attracted to IBM’s new environment. IBM went in the wrong direction with their in-home language


Posted by: Jim Mooney
 
August 9, 2013
2:04 pm

Wow. The possibilities are astounding.


Posted by: Von Chucwuemeca
 
August 8, 2013
12:05 pm

The future of computing and medicine will definitely be intertwined because the way a human being functions and a computer functions are quite similar as far as I am concerned.

Molecular biology is the key to this breakthrough and my gut feeling is that it also requires Nano technology to play a big part in paving the way for Human and Computer communication.

The communication would be at the molecular level or at the atomic or sub atomic particle level. Why at this level, well everything is made up of the same substance at the atomic level hence the communication between the same substance will be easier or less complex (not that it is an easy plug and play matter, it will be a tough bridge to cross initially).

Once the mode of communication has been established, it would be only a matter of time before human communication signals from within the body would be intercepted by an external computer and help diagnose a normal signal and a distress signal (detecting ailing body parts).

This could pave the way to crack the secrets of the mind and explore the vast storage facilities of the brain using Nano receptors implanted in a human temple and communicated wireless to the diagnosing computer.

This will also pave the way for thought signal transmission.

Once the communication patterns from a brain is understood Nano memory chips could be used to restore damaged brain sections and help generate the required signals to restore non functioning signals to limbs etc.,

Nano technology can be used to repair spinal cord damages by implanting Nano signal conveyors or signal boosters to give continuity to the signal for normal body functioning.

Well how do I know all these stuff?? I simply keep dreaming of this on and off and felt I should blurt it out to someone like you folks who might be receptive and act on it.


Posted by: Anas Sheriffdeen
 
12 Trackbacks
 
April 14, 2014
12:21 am

[…] IBM is announcing DARPA SyNAPSE Phase 3 that builds on Phase 0, Phase 1, and Phase 2. See here for my perspective on the significance of the results being announced. See here for a video […]


Posted by: DARPA SyNAPSE Phase 3 & A New Foundation to Program SyNAPSE Chips | Yottabyte computer
 
April 13, 2014
6:09 pm

[…] IBM is announcing DARPA SyNAPSE Phase 3 that builds on Phase 0, Phase 1, andPhase 2. See here for my perspective on the significance of the results being announced. See here for a video […]


Posted by: Cognitive computing | Big Data Analytics
 
April 13, 2014
6:00 pm

[…] IBM is announcing DARPA SyNAPSE Phase 3 that builds on Phase 0, Phase 1, andPhase 2. See here for my perspective on the significance of the results being announced. See here for a video […]


Posted by: Cognitive computing | Yottabyte computer
 
April 13, 2014
5:55 pm

[…] IBM is announcing DARPA SyNAPSE Phase 3 that builds on Phase 0, Phase 1, andPhase 2. See here for my perspective on the significance of the results being announced. See here for a video […]


Posted by: Cognitive computing | Big Data Hub
 
April 13, 2014
5:51 pm

[…] IBM is announcing DARPA SyNAPSE Phase 3 that builds on Phase 0, Phase 1, andPhase 2. See here for my perspective on the significance of the results being announced. See here for a video […]


Posted by: Cognitive computing |
 
April 3, 2014
9:22 am

[…] beauty with practicality,” he says. After years of hard work and difficult decisions, his team’s designs are proving […]


Posted by: IBM Fellows: Transforming Computing, Society and IBM « A Smarter Planet Blog A Smarter Planet Blog
 
October 14, 2013
9:23 am

[...] low-power, and compact size of the human brain. In the face of tremendous technical unknowns, our goal is now within reach.This was no easy journey. As the principal investigator, I had to coordinate the activities of [...]


Posted by: Management Lessons from the Cognitive Chip Development Project | IBMJobs
 
October 14, 2013
7:12 am

[...] Five years ago, a team made up of scientists from IBM, several universities and two US national laboratories embarked on a great quest: to design a computer chip inspired by the function, low-power, and compact size of the human brain. In the face of tremendous technical unknowns, our goal is now within reach. [...]


Posted by: Management Lessons from the Cognitive Chip Development Project « A Smarter Planet Blog A Smarter Planet Blog
 
August 25, 2013
12:35 pm

[...] A New Era of Computing Requires a New Way to Program Computers [...]


Posted by: Big Data, IOT and M2M- What’s trending on Twitter?
 
August 9, 2013
12:28 pm

[...] at the Smarter Planet Blog, Dharmendra S. Modha writes that, just as Fortran powered the last 60 years of scientific [...]


Posted by: Corelets – A New Paradigm for Cognitive Computing | insideHPC.com
 
August 9, 2013
10:44 am

[...] Smarter Planet: A New Era of Computing Requires a New Way to Program Computers [...]


Posted by: IBM Scientists Create Brain-Like Computer Architecture | IBM Official Alumni Group: The Greater IBM Connection
 
August 8, 2013
4:45 am

[...] technology when compared to today’s so-called von Neumann architectures and computers. Dr. Dharmendra S. Modha, Principal Investigator and Senior Manager, IBM Research, offered this [...]


Posted by: IBM Announces Breakthrough Sensory Tech
 
Post a Comment