Synapses Super Computer Technology Mimics the Human Brain capable of processing large-scale data as well as the human brain's ability. Be able to solve the problem by yourself. Now researchers have discovered microscopic gadgets that mimic the connections between neurons in the human brain that overstate existing computer technologies.
This latest research can make the robot have self-driving car capability, data mining, medical diagnosis, stock-trading analysis and "other human interactive smart systems on future machines," said Tae-Woo Lee, a scientistat material that is Pohang University of Science Technology in Korea and senior author of the study.
The enormous human brain computing power comes from the connection between its neurons. Research shows that the human brain has about 100 billion neurons and about 1 quadrillion (1 million billion) cable connections of these cells are interconnected. In each of these connections, or synapses, neurons usually fire about 10 times per second.
In principle, the human brain can perform about 10 quadrillion operations per second. By comparison, the world's fastest supercomputer, Tianhe-2 in China, is capable of carrying up to about 55 quadrillion calculations per second, according to the TOP 500 project, which ranks among the 500 most powerful computers in the world. However, previous research shows that the human brain consumes only about 20 watts of power, which is barely enough to run a dim light bulb, while Tianhe-2 consumes about 17.8 megawatts of electricity, which is enough to run about 900,000 light bulbs.
Synapses Super Computer Technology Mimics the Human Brain
Scientists want to build computers that mimic the performance of the human brain with low power usage. "The development of synapses is rumored to be comparable to the biological systems of the human brain and will be a major step in the computer world," Lee Live Science said.
To date, artificial synapses consume more energy than biological synapses. Previous research has shown that biological synapses consume about 10 femtojoules each time a fire neuron. Now, Lee and his colleagues have created an artificial synapses that require only about 1.23 femtojoules per synaptic event, making their synapses artificially require the lowest power. (For comparison, a small apple falling about 3.3 feet (1 meter) to Earth will produce about 1 quadrillion femtojoules of kinetic energy.)
This study shows that "energy consumption and memory of artificial brain density can ultimately compete, and even exceed, human biological brain in the future," Lee said.
This new artificial synapse is a type of transistor, or an electronic switch. By turning on and off automatically, they can replicate how the synapse fires.
The researchers fabricated 144 synaptic transistors on a 4-inch (10-centimeter) wafer. At the heart of this device uses cables with a width of 200 to 300 nanometers (billionths of a meter). (By comparison, the average human hair width is about 100,000 nanometers). "The very small size feature of this device helps to lower the amount of energy consumed", say the researchers.
New device made of one kind of organic material. These materials help synapses artificially capture or release electrically charged ions, mimicking how biological synapses work.
What do you think?
In essence, Synapses has a work system capable of stopping or executing a command and calculation automatically, without human help. Computers today, the main instruction is still done by humans.
In the future there will really be such robots in the transformer film. They are able to think, decide, find solutions and solve problems independently.
0 Response to "Synapses Super Computer Technology Mimics the Human Brain"
Post a Comment