Quantum Dot Chips to AI’s rescue
If one were to pick any modern technology at random, chances are that it wouldn’t surpass the scale of publicity that the likes of AI and Neural Networks have received.
The buzz is partly justified - the idea of 'learning' machines is a fascinating and useful one. Still, corporations and businesses are yet to exploit AI completely for their purposes. One of the biggest hurdles to fully enabling the use of AI in industrial settings rests with a component of computing that is sometimes overlooked due to all the hype - memory and computational efficiency. Many systems such as speech and face recognition systems and IoT enabled devices for remote health monitoring normally require computationally heavy and energy-intensive neural networks making it difficult to perform these computations on the portable hand-held devices.
An indigenous quantum breakthrough
However, there have been progresses to gap the bridge between data and the necessary hardware to process it efficiently. The latest of these developments comes from Indian Institute of Technology, Hyderabad, where researchers have developed Magnetic Quantum-dot Cellular Automata (MQCA) based nanomagnetic logic architectural design methodology of approximate arithmetic circuits, according to a release shared by the institute. The researchers are working towards resource constrained magnetic chips for ultra low power portable AI applications.
"We now aim for a bigger goal by porting some power-hungry AI applications on such indigenously developed ultra-low-power computing platform,” said Santhosh Sivasubramani, one of the researchers in the team. The other researchers in the team at IIT Hyderabad include Amit Acharyya, associate professor and Chandrajit Pal, post-doctoral research fellow.
The discreteness of quantum dots as applied to automata
Quantum dot cellular automata are a proposed improvement on conventional computer design (CMOS), which have been devised in analogy to conventional models of cellular automata introduced by John von Neumann. A cellular automaton (CA) is a dynamic discrete system consisting of a uniform (finite or infinite) grid of cells. Each cell can be in only one of a finite number of states at a time. Any device designed to represent data and perform computation, regardless of the physics principles it exploits and materials used to build it, must have two fundamental properties: distinguishability and conditional change of state, the latter implying the former. This means that such a device must have barriers that make it possible to distinguish between states and that it must have the ability to control these barriers to perform a conditional change of state. For example, in a digital electronic system, transistors play the role of such controllable energy barriers, making it extremely practical to perform computing with them.
In 1993, a physical implementation of an automaton using quantum-dot cells was proposed. The automation quickly gained popularity and it was first fabricated in 1997. The discrete nature of both cellular automata and quantum mechanics was combined to create nano-scale devices capable of performing computation at very high switching speeds (order of Terahertz) and consuming extremely small amounts of electrical power.
“Performing AI computing on edge with approximate nanomagnetic logic deployed on the magnetic ICs is an attempt towards the futuristic computations,” Acharyya said.
\\Archi Banerjee
