Google says it has developed artificial intelligence software that can design computer chips faster than humans.
Google is using machine learning to help design the next generation of machine learning chips. The company’s engineers say the algorithm designs are comparable to or superior to those created by humans, and can be created much faster.
The search giant said in research paperA chip that would take humans months to design could be devised by a new AI in less than six hours.
The company indicated that artificial intelligence was used to develop the latest version of Google’s Tensor processing unit chips.
Read also: WhatsApp makes chatting with businesses easier and faster
“Our production method was used to design the next generation of Tensor CPU chips,” wrote the authors of the paper, led by the Head of Machine Learning for Systems at Google.
In other words, Google uses AI to design chips that can be used to create more sophisticated AI systems.
Specifically, Google’s new system can map out the slice.
This mainly includes layout where components such as CPUs, GPUs, and memory are placed across a silicon mold in relation to each other.
Placing these components across these small boards is important because it affects chip power consumption and processing speed.
Also Read: Tesla Uses In-Car Camera To Monitor Drivers
Google artificial intelligence:
It takes humans months to design these schemas optimally. But Google’s deep reinforcement learning system can do so with relatively little effort.
Similar systems can also defeat humans in complex games like Go and chess. In these scenarios, algorithms are trained to move the pieces that increase their chances of winning the game.
But in a chip scenario, the system is trained to find the best combination of components to make it as computationally efficient as possible.
The system was fed 10,000 chip charts in order to see what worked and what didn’t.
Whereas human chip designers typically lay out components in neat lines, Google’s AI uses a more dispersed approach to designing its chips.
It is reported that this is not the first time that artificial intelligence has succeeded after learning how to perform a task after feeding it with human data.
The famous artificial intelligence AlphaGo from DeepMind unconventional move Extremely against the Go World Champion in 2016 that astounded Go players all over the world.
And Google engineers pointed out in the research paper that the hack could have major implications for the semiconductor sector.
Facebook’s chief AI scientist praised the research, describing it as “very cool work” via platform Twitter, adding that this is where enhanced learning in AI shines.
The breakthrough was hailed as an important achievement that will significantly help accelerate the supply chain.
Read also: Samsung develops Exynos chip with ray tracing