AI Mimics The Way Human Brain Completes Tasks With Help Of New Artificial Synapse
With the help of the AI, the machine can now talk with us, recolonize eye diseases and even write poetry.
Taking Artificial Intelligence one step ahead, a team of US researchers has created an artificial synapse. It is an artificial version of the space over which neurons communicate.
This Artificial synapse helps computers to mimic one piece of the brain. It helps the machine to process information like a digital computer does but also like a human brain completes any task.
The major problem with the AI system is that they demand a high-end hardware configuration, which ultimately makes the machine high energy-consuming devise.
With the help of this newly developed Artificial synapse, we can build energy-efficient AI devices that would revolutionize our lives.
Dr. Feng Xiong, Assistant Professor of Electrical and Computer Engineering said “The analog nature and massive parallelism of the brain are partly why humans can outperform even the most powerful computers when it comes to higher-order cognitive functions such as voice recognition or pattern recognition in complex and varied data sets,”
The human brain has trillions of synapses for transmitting information, so building a brain with digital devices was a very complex task for researchers. To mimic one analog synapse, it will take about a dozen digital device.
Therefore instead of carrying out computations based on binary, on/off signal, like digital chips do today. The elements of a “brain on a chip” here work in an analog fashion, exchanging a gradient of signals.
In this way, small neuromorphic chips could work like the brain. With the help of this chipset, they can efficiently process millions of streams of parallel computations that are currently only possible with large banks of supercomputers.
Xiong Lab’s approach provides a possible route for the hardware implementation of large-scale artificial neural networks.
An emerging field called “neuromorphic computing” focuses on the design of computational hardware inspired by the human brain. Dr. Xiong and his team built graphene-based “artificial synapses” in a 2D honeycomb configuration of carbon atoms.
The Graphene synapse demonstrated excellent energy efficiency just like biological synapses, said the study published in the journal Advanced Materials. However, Artificial Synapse still uses about 10,000 times as much energy as the minimum a biological synapse needs in order to fire.
The graphene-based neural networks can be employed in flexible and wearable electronics to enable computation at the edge of the Internet. Graphene’s conductive properties allowed the researchers to finely tune their electrical conductance.
Dr. Xiong said, “By empowering even a rudimentary level of intelligence in wearable electronics and sensors, we can track our health with smart sensors, provide preventive care and timely diagnostics, monitor plants growth and identify possible pest issues, and regulate and optimize the manufacturing process.”
The development of an artificial brain that functions like the analog human brain still requires a number of breakthroughs, said, researchers. There is a need to find the right configurations to optimize these new “artificial synapses”.
Despite the challenges, Dr. Xiong said he’s optimistic about the direction they’re headed.
“We are excited about this progress since it can potentially lead to the energy-efficient, hardware implementation of neuromorphic computing, which is currently carried out in power-intensive GPU clusters,” he noted.
The ability of Artificial Synapse of communicating with live neurons will ultimately lead to improved brain-machine interfaces. The softness and flexibility of the device also lend itself to being used in biological environments.
What do you think is it possible to build something as powerful as a human brain.
More in AI :
Harvard And Google Created An AI That Predicts Earthquake Aftershocks
This New AI Tells Whether You’re Gay or Straight Just By Your Photograph
Artificial Intelligence (AI) Could Create 7.2 Million Jobs, More Than It Destroys – PwC Report