Super-efficient AI software developed to run on smartphones without internet access
Image credit: Dreamstime
New deep-learning artificial intelligence (AI) software has been developed that is drastically reduced in size, so that it can fit onto a chip that can be embedded into smartphones and wearable devices.
Currently, the software used to run AI from smartphones, such as voice control, requires internet access so that commands can be processed in the cloud.
Now, a team at the University of Waterloo in Canada had made software that boasts a 200-fold reduction in size compared to other forms of deep-learning AI software.
This allows AI to break free of the internet and cloud computing and operate independently while using AI that performs almost as well as tethered neural networks.
“We feel this has enormous potential,” said Alexander Wong, professor at Waterloo and co-creator of the technology. “This could be an enabler in many fields where people are struggling to get deep-learning AI in an operational form.”
The use of stand-alone deep-learning AI could lead to much lower data processing and transmission costs, greater privacy and use in areas where existing technology is impractical due to expense or other factors.
Deep-learning AI, which mimics the human brain by processing data through layers and layers of artificial neurons, typically requires considerable computational power, memory and energy to function.
Researchers took a page from evolutionary forces in nature to make that AI far more efficient by placing it in a virtual environment, then progressively and repeatedly depriving it of resources.
The deep-learning AI responds by adapting and changing itself to keep functioning each time computational power and memory are taken away.
“These networks evolve themselves through generations and make themselves smaller to be able to survive in these environments,” said engineering research professor Mohammad Javad Shafiee.
When put on a chip and embedded in a smartphone, such compact AI could run its speech-activated virtual assistant and other intelligent features, greatly reducing data usage and operating without internet service.
Other potential applications range from use in low-cost drones and smart grids, to surveillance cameras and manufacturing plants, where there are significant issues around streaming sensitive or proprietary data to the cloud.
Wong and Shafiee, who have co-founded a company called DarwinAI to commercialise their efficient AI software, were “amazed” at the results when they first attempted their approach to evolving deep-learning AI about three years ago.
“We are researchers, so we explore many different things,” said Shafiee. “And if it works, we keep going and push harder.”
A recent government report found that AI could contribute £630bn to the UK economy by 2035 if funds are allocated for research initiatives.