IBM has been working on this for awhile with DARPA funding and now another round of funding to continue work.
Two chips completed and more planned.
Now where will we see them used?
For some defense project or could we get a smart robot to do some Lunar field geology?
Hmmm, how about AMEE from the movie Red Planet.
------------------------------
snip
Red Planet (2000)
AMEE (Autonomous Mapping Exploration and Evasion)This unsuccessful science fiction thriller film followed a small, six-person team of astronauts on an investigative rescue operation to the red planet of Mars in the year 2045, led by pretty Commander Kate Bowman (Carrie-Anne Moss). Their mission was to investigate further terraforming of Mars for future human colonization.
During a solar flare incident and subsequent shipwreck on the planet, a multi-purpose, unspeaking quadripedal (crouching) or bipedal (7 foot tall) robot named AMEE, an ex-military android (completely CGI-created) designed for mapping and exploration of the Martian surface, was damaged in the crash and reverted to its original programming as a hunter/killer.
The android stalked the crew members with its infra-red and X-ray vision. The metallic, skeletal monkey-like AMEE had four limb appendages with joints that swiveled, turned, pivoted, and spun around, and clawlike 'fingers'.
snip
------------------------------
Best view the videos now. Who knows how long we will hear about it.
- LRK -
------------------------------
IBM unveils cognitive computing chips, combining digital ‘neurons’ and ‘synapses’
August 18, 2011 by Editor
IBM researchers unveiled today a new generation of experimental computer chips designed to emulate the brain’s abilities for perception, action and cognition.
In a sharp departure from traditional von Neumann computing concepts in designing and building computers, IBM’s first neurosynaptic computing chips recreate the phenomena between spiking neurons and synapses in biological systems, such as the brain, through advanced algorithms and silicon circuitry.
The technology could yield many orders of magnitude less power consumption and space than used in today’s computers, the researchers say. Its first two prototype chips have already been fabricated and are currently undergoing testing.
Called cognitive computers, systems built with these chips won’t be programmed the same way traditional computers are today. Rather, cognitive computers are expected to learn through experiences, find correlations, create hypotheses, and remember — and learn from — the outcomes, mimicking the brains structural and synaptic plasticity.
snip
[See videos - LRK -]
------------------------------A little different write up.
- LRK -
------------------------------
According to a press release that crossed the wire today, IBM researchers have been able to develop prototype processors that function less like current CPUs and more like a human brain. The experimental chips are reportedly designed to emulate a brain’s abilities for perception, action and cognition.
The so called neurosynaptic computing chips were designed to recreate the relationship between spiking neurons and synapses in biological systems, like the human brain. The chips do not contain any biological elements, however, but rather function using advanced embedded algorithms and custom silicon circuitry. IBM’s first two prototype chips have already been fabricated using 45 nm SOI-CMOS process technology and are currently undergoing testing. The chips contain 256 silicon neurons and one core contains 262,144 programmable “synapses”, the other 65,536 learning “synapses”.
In lieu of current programming models, future system built using this type of chip are expected to learn through experiences, find correlations, create hypotheses, and remember mimicking a biological brain. The team at IBM has successfully demonstrated simple applications like navigation, machine vision, pattern recognition, associative memory and classification already. And the company’s long-term goal is to build a chip system with ten billion neurons and a hundred trillion synapses, while consuming only one kilowatt of power and occupying less than two liters of volume.
The so called neurosynaptic computing chips were designed to recreate the relationship between spiking neurons and synapses in biological systems, like the human brain. The chips do not contain any biological elements, however, but rather function using advanced embedded algorithms and custom silicon circuitry. IBM’s first two prototype chips have already been fabricated using 45 nm SOI-CMOS process technology and are currently undergoing testing. The chips contain 256 silicon neurons and one core contains 262,144 programmable “synapses”, the other 65,536 learning “synapses”.
In lieu of current programming models, future system built using this type of chip are expected to learn through experiences, find correlations, create hypotheses, and remember mimicking a biological brain. The team at IBM has successfully demonstrated simple applications like navigation, machine vision, pattern recognition, associative memory and classification already. And the company’s long-term goal is to build a chip system with ten billion neurons and a hundred trillion synapses, while consuming only one kilowatt of power and occupying less than two liters of volume.
snip
[Has video presentation - LRK -]
------------------------------
I wonder if the University students are learning how to program the chips.
- LRK -
------------------------------
http://www.techspot.com/news/
IBM unveils cognitive computing chips that mimic human brain
By Shawn Knight
On August 18, 2011, 12:00 PM ES
Fans of the 'Terminator' franchise might sleep a little uneasy tonight as IBM, teaming with the Defense Advanced Research Projects Agency (DARPA) and four universities, has designed the first working computer chips modeled after the human brain.
In the popular film series, Skynet is an artificial intelligence system built by Cyberdyne Systems for the US armed forces. The goal was to remove the possibility of human error and provide an efficient response to incoming enemy attacks, but things went horribly wrong when the system became self-aware and turned on humanity.
The project is called Synapse (Systems of Neuromorphic Adaptive Plastic Scalable Electronics, stylized as SyNAPSE), based on the junction between neurons and other cells in the nervous system. Dharmendra Modha is the chief investigator of the project and a researcher at IBM Almaden Research Center in San Jose, California.
“This is the seed for a new generation of computers, using a combination of supercomputing, neuroscience, and nanotechnology,” Modha said in an interview with VentureBeat. ”The computers we have today are more like calculators. We want to make something like the brain. It is a sharp departure from the past.”
snip
------------------------------
This from IBM and has other references in their text.
- LRK -
------------------------------
IBM Unveils Cognitive Computing Chips
ARMONK, N.Y., - 18 Aug 2011: Today, IBM (NYSE: IBM) researchers unveiled a new generation of experimental computer chips designed to emulate the brain’s abilities for perception, action and cognition. The technology could yield many orders of magnitude less power consumption and space than used in today’s computers.
In a sharp departure from traditional concepts in designing and building computers, IBM’s first neurosynaptic computing chips recreate the phenomena between spiking neurons and synapses in biological systems, such as the brain, through advanced algorithms and silicon circuitry. Its first two prototype chips have already been fabricated and are currently undergoing testing.
Called cognitive computers, systems built with these chips won’t be programmed the same way traditional computers are today. Rather, cognitive computers are expected to learn through experiences, find correlations, create hypotheses, and remember – and learn from – the outcomes, mimicking the brains structural and synaptic plasticity.
To do this, IBM is combining principles from nanoscience, neuroscience and
The goal of SyNAPSE is to create a system that not only analyzes complex information from multiple sensory modalities at once, but also dynamically rewires itself as it interacts with its environment – all while rivaling the brain’s compact size and low power usage. The IBM team has already successfully completed Phases 0 and 1.
“This is a major initiative to move beyond the von Neumann paradigm that has been ruling computer architecture for more than half a century,” said Dharmendra Modha, project leader for IBM Research. “Future applications of computing will increasingly demand functionality that is not efficiently delivered by the traditional architecture. These chips are another significant step in the evolution of computers from calculators to learning systems, signaling the beginning of a new generation of computers and their applications in business, science and government.”
snip
------------------------------
More information from way back in 2008 with a list of collaborators.
Maybe you know some of them.
- LRK -
------------------------------
http://modha.org/blog/2008/11/
Dharmendra S Modha's Cognitive Computing Blog
Dharmendra S Modha's Cognitive Computing Blog
"to engineer the mind by reverse engineering the brain
IBM has officially announced that our proposal “Cognitive Computing via Synaptronics and Supercomputing (C2S2)” won the first phase of DARPA’s Systems of Neuromorphic Adaptive Plastic Scalable Electronics (SyNAPSE) initiative. Please see DARPA’s BAA here. Some Snippets from the BAA:
“Proposed research should investigate innovative approaches that enable revolutionary advances in neuromorphic electronic devices that are scalable to biological levels. Specifically excluded is research that primarily results in evolutionary improvements to the existing state of practice.”
“Over six decades, modern electronics has evolved through a series of major developments (e.g.,transistors, integrated circuits, memories, microprocessors) leading to the programmable electronic machines that are ubiquitous today. Owing both to limitations in hardware and architecture, these machines are of limited utility in complex, real-world environments, which demand an intelligence that has not yet been captured in an algorithmic-computational paradigm. As compared to biological systems for example, today’s programmable machines are less efficient by a factor of one million to one billion in complex, real-world environments. The SyNAPSE program seeks to break the programmable machine paradigm and define a new path forward for creating useful, intelligent machines.”
“The vision for the anticipated DARPA SyNAPSE program is the enabling of electronic neuromorphic machine technology that is scalable to biological levels. Programmable machines are limited not only by their computational capacity, but also by an architecture requiring (human-derived) algorithms to both describe and process information from their environment. In contrast, biological neural systems (e.g., brains) autonomously process information in complex environments by automatically learning relevant and probabilistically stable features and associations. Since real world systems are always many body problems with infinite combinatorial complexity, neuromorphic electronic machines would be preferable in a host of applications—but useful and practical implementations do not yet exist.”
“Proposed research should investigate innovative approaches that enable revolutionary advances in neuromorphic electronic devices that are scalable to biological levels. Specifically excluded is research that primarily results in evolutionary improvements to the existing state of practice.”
“Over six decades, modern electronics has evolved through a series of major developments (e.g.,transistors, integrated circuits, memories, microprocessors) leading to the programmable electronic machines that are ubiquitous today. Owing both to limitations in hardware and architecture, these machines are of limited utility in complex, real-world environments, which demand an intelligence that has not yet been captured in an algorithmic-computational paradigm. As compared to biological systems for example, today’s programmable machines are less efficient by a factor of one million to one billion in complex, real-world environments. The SyNAPSE program seeks to break the programmable machine paradigm and define a new path forward for creating useful, intelligent machines.”
“The vision for the anticipated DARPA SyNAPSE program is the enabling of electronic neuromorphic machine technology that is scalable to biological levels. Programmable machines are limited not only by their computational capacity, but also by an architecture requiring (human-derived) algorithms to both describe and process information from their environment. In contrast, biological neural systems (e.g., brains) autonomously process information in complex environments by automatically learning relevant and probabilistically stable features and associations. Since real world systems are always many body problems with infinite combinatorial complexity, neuromorphic electronic machines would be preferable in a host of applications—but useful and practical implementations do not yet exist.”
snip
------------------------------
When will we see the chip in a new tablet computer that we can use for smart computing.
Make sure it has high resolution cameras to aid in doing land surveys and has enhanced pattern recognition algorithms.
How many folks are involved in this project? And if the $21 million were to be cut? (we don't have any money for real)
- LRK -WordPress: http://lrkellogg.
==============================
FEBRUARY 09, 2009
DARPA has funded the Synapse Program which seeks to break the programmable machine paradigm and define a new path forward for creating useful, intelligent machines. As compared to biological systems for example, today’s programmable machines are less efficient by a factor of one million to one billion in complex, real-world environments. The Synapse program is trying to build an electronic element like a brain synapse and then scale to brain levels. They are targeting 220 trillion synapses for a human cerebral cortex, which is 400 times larger than a recently completed rat cortex simulation. A successful synapse circuit will be 20 or more times better than a transistor for simulating a brain.
In the next 9 months (Nov 2008-Aug 2009), the research teams will focus on demonstrating nano-scale, low power synapse-like devices and on beginning to uncover the functional microcircuits of the brain.
In the next 9 months (Nov 2008-Aug 2009), the research teams will focus on demonstrating nano-scale, low power synapse-like devices and on beginning to uncover the functional microcircuits of the brain.
snip
==============================
HRL and SyNAPSE
By Massimiliano Versace | August 25, 2008
The following has ben published on Topix. It is one of the few articles around NOT on IBM.... Dr. Narayan Srinivasa talks about the program. HRL has a long and successful track record in modeling complex cognitive inspired architectures, which ultimately will be a great advantage in the SyNAPSE program when it will be the time to actually use the chip to perform meaningful computations. Note the typo in the article "'The follow-on phases of the project will create a technology that functions like the brain of a cat, which comprises 108 neurons and 1012 synapses,' Srinivasa said. 'The human brain has roughly 1011 neurons and 1015 synapses." The formatting got obviously screwed up... we are talking about 10^11 and 10^15 (otherwise, a cell phone chip will suffice...).
- HRL Laboratories, LLC, will begin pioneering research to develop electronics that will simulate the cognitive capabilities and efficiencies of the biological brain.
The daunting undertaking is part of the Defense Advanced Research Project Agency's (DARPA) SyNAPSE, or Systems of Neuromorphic Adaptive Plastic Scalable Electronics, program. HRL will lead a group of industry and university research laboratories with expertise in core areas of neuro and cognitive science in the groundbreaking research.
Despite exponential advances in computing technology over the last decade, the limitations of hardware and architecture prohibit computers from functioning independently in real-world scenarios. The goal of the SyNAPSE program is to bridge biology and electronics and establish a new paradigm for creating more intelligent machines that can interact with, react to, and actually learn from their environments.
'Two things are enabling us to establish this new paradigm,' said Dr. Narayan Srinivasa, SyNAPSE Program Manager and Senior Scientist in HRL's Information and System Sciences Office. 'First is the advancement in microelectronics, which provides us greater density and speed at much lower power consumption than ever before. The other is a better understanding of neuroscience and how the brain functions at the synaptic, neuronal, network, and system levels.'
The HRL team's ultimate goal is to build a low-power, compact electronic chip combining a novel analog circuit design and a neuroscience-inspired architecture that can address a wide range of cognitive abilities--perception, planning, decision making, and motor control. In the initial two phases of the SyNAPSE program, the team will translate the neuronal and synaptic functions of the biological cortex into similar microelectronic functions.
snip==============================
WHAT THE MIND CAN CONCEIVE, AND BELIEVE, IT WILL ACHIEVE - LRK -
==============================
No comments:
Post a Comment
Note: Only a member of this blog may post a comment.