TECH in AMERICA (TiA)

SHARING AMERICA'S TECH NEWS FROM THE VALLEY TO THE ALLEY

Systems that Perceive, Think, and Act

Technological advances are allowing scientists to begin building a  cognitive computer that functions like a brain.IBM_injector_human[1]

by Dr. Dharmendra Modha, Manager of  Cognitive Computing, IBM      IBM_CC_article3_image-thumb-630x435-124151[1]

Since computers were invented, they’ve been called “brains.”

Yet, the fundamental tasks at which computers and human brains excel, the  vastly different design underlying each, and the brain’s remarkable ability to  learn and adapt has always set them poles apart — until now.
By bringing together the recent advances in neuroscience, supercomputing, and nanotechnology, we’re at the beginning stages  of creating cognitive machines: inspired by the function, low power, and compact  volume of the organic brain.
The world needs these new approaches and needs them now.  We’re  populating the Earth and Space with sensors, cameras, and microphones. But, the  needle of information is lost in a haystack, nay, an ocean of data.   Processing this tsunami of real-time, parallel, spatio-temporal,  multi-modal data would be too expensive in power and too slow in speed of  response for traditional machines, but would be ideal for a brain-like computer.   Even more urgently, today’s computers are hitting physical and  architectural limits in their size and speed.
Modern computers are designed in the image of ENIAC, the first digital computer created in  1946, which defined what came to be known as the von Neumann architecture. Computers were meant  for calculation and for handling precise, symbolic data. They separate memory  from computation, have centralized processing, handle data sequentially, require  programming, operate synchronously in a clock-driven fashion, are fast, and, as  a result, are energy-hungry and hot.
The brain’s neurons and synapses, however, form a network. The brain  evolved millions of years ago in the savannah for solving the basics: getting  food, fighting, fleeing, and mating and is meant for handling low-resolution,  ambiguous, sub-symbolic data. It integrates memory (synapses) and computation  (neurons), has distributed processing, handles data in parallel, has learning,  operates asynchronously in an event-driven fashion, is slow, and, as a result,  is energy-efficient and cool.
Under the auspices of Defense Advanced Research Projects Agency‘s SyNAPSE program,  IBM and several leading universities have been working on the challenge since  2008.
IBM_injector_human.jpg
Organic technology akin to the brain’s doesn’t exist today and developing  it would require too much time and money. Meanwhile, the pressing problem of  data deluge cannot be delayed. So our key innovation is a new non-von Neumann,  modular, parallel, distributed, event-driven, scalable architecture: one that  can be synthesized in today’s technology and simultaneously serves as a beacon  for future technology to come. The new architecture, in turn, necessitates an  entirely new way of thinking, programming, and learning. This is cognitive  computing — a new synthesis of silicon and software.
As a first step, in 2011, we demonstrated tiny cognitive chips, at the scale of a worm’s  nervous system. We taught the chips to play Pong, one of the earliest computer games, and  demonstrated capabilities such as navigation, machine vision and pattern  recognition. Our next-generation chip will graduate from the nervous system of  worms to the nervous system of a bee. The end game is to demonstrate a system  with 100  trillion synapses, at roughly human-scale that occupies merely two liters  while consuming barely one kilowatt of power. To power the same capability on  today’s computers would require, arguably, a nuclear reactor. In contrast, we  want to build, literally, a brain-in-a-box!
The quest will require significant time, resources, and innovation, but  will unleash a cognitive computing revolution. These new systems will pull data,  including sights, sounds, and smells, from massive arrays of sensors and draw  conclusions from them, turning the sensors themselves into computers.
In the future, these chips could power low-energy, light-weight glasses  that help blind people navigate; “eyes” that let robots and cars see;  health-care systems that monitor blood pressure, temperature, and oxygen levels  of the elderly at home and send alerts before problems occur; and systems that  measure the tide, air, and wind speed to predict tsunamis.
These cognitive computing chips and today’s existing computers will  complement each other, like yin and yang, mapping new ways to improve the  world’s productivity and sustainability.

Thank you. TiA.

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

Information

This entry was posted on June 18, 2013 by in SCITECH and tagged , , , , , , , .

Top Posts & Pages

POSTS

Enter your email address to follow this blog and receive notifications of new posts by email.

TEAM TiA!

%d bloggers like this: