[ad_1]
A graphic illustration showing how the technology combines the basic software needed to drive AI with image capture hardware, into a single electronic device. Credit: RMIT University
Prototype technology reduces AI to deliver brain-like functionality in one powerful device.
Researchers have developed artificial intelligence technology that brings together imaging, processing, machine learning and memory into an electronic chip, powered by light.
The prototype reduces artificial intelligence technology by mimicking the way the human brain processes visual information. Advancement at the nanoscale combines the basic software needed to drive artificial intelligence with image capture hardware into a single electronic device.
With further development, the light-driven prototype could enable smarter and smaller autonomous technologies like drones and robotics, as well as smart wearables and bionic implants like artificial retinas.
The study, led by an international team of Australian, American and Chinese researchers led by RMIT University, was published in the journal Advanced material.
Lead researcher Associate Professor Sumeet Walia, of RMIT, said the prototype provided brain-like functionality in a powerful device.
The AI chip powered by light: prototype technology that combines imaging, processing, machine learning and memory. Credit: RMIT University
“Our new technology radically increases efficiency and precision bringing multiple components and features into one platform, “said Walia.
“It is bringing us closer to an all-in-one AI device inspired by nature’s greatest computing innovation: the human brain.
“Our aim is to replicate a fundamental feature of the way the brain learns by imprinting vision as memory. The prototype we have developed represents an important leap forward towards neurorobotics, better technologies for human-machine interaction and scalable bionic systems. “
Total package: AI improvement
Artificial intelligence typically relies heavily on software and off-site data processing. The new prototype aims to integrate electronic hardware and intelligence together, for quick decisions on site.
“Imagine a dash cam in a car integrated with our neuro-inspired hardware: this means it can recognize lights, signs, objects and make immediate decisions, without having to connect to the Internet,” Walia, who co-leads the functional materials and Microsystems Research Group at RMIT, he said.
“By bringing everything together on a single chip, we can deliver unprecedented levels of efficiency and speed in autonomous and AI-driven decision making.”
Associate Professor Sumeet Walia and Dr Taimur Ahmed, RMIT University. Credit: RMIT University
The technology is based on an earlier chip prototype from the RMIT team, which used light to create and modify memories.
The new built-in features mean the chip can now automatically acquire and enhance images, classify numbers, and be trained to recognize patterns and images with an accuracy rate of over 90%.
The device is also easily compatible with existing electronics and silicon technologies, for effortless future integration.
Seeing the light: how technology works
The prototype is inspired by optogenetics, an emerging tool in biotechnology that allows scientists to delve into the body’s electrical system with great precision and use light to manipulate neurons.
The AI chip is based on an ultra-thin material – black phosphor – which changes electrical resistance in response to different wavelengths of light. The different functionalities like imaging or memory storage are achieved by shining different colors of light on the chip.
The lead author of the study, RMIT’s Dr Taimur Ahmed, said light-based computation is faster, more accurate, and requires far less energy than existing technologies.
“By packing so many core capabilities into a compact nano-scale device, we can broaden the horizons for machine learning and artificial intelligence to integrate into smaller applications,” Ahmed said.
“Using our chip with artificial retinas, for example, would allow scientists to miniaturize that emerging technology and improve the accuracy of the bionic eye.
“Our prototype represents a significant advance towards the ultimate in electronics: a brain on a chip that can learn from its environment just like us.”
This work was performed in part at the Micro Nano Research Facility (MNRF) at RMIT, with support from RMIT Microscopy and Microanalysis Research Facility (RMMF), National Computational Infrastructure Australia (NCI), Multimodal Australian Sciences Imaging and Visualization Environment (MASSIVE ) and Pawsey Supercomputing Facility.
Reference: “Fully light-controlled memory and neuromorphic computation in layered black phosphorus” by Taimur Ahmed, Muhammad Tahir, Mei Xian Low, Yanyun Ren, Sherif Abdulkader Tawfik, Edwin LH Mayes, Sruthi Kuriakose, Shahid Nawaz, Michelle JS Spencer, Hua Chen , Madhu Bhaskaran, Sharath Sriram and Sumeet Walia, November 17, 2020, Advanced material.
DOI: 10.1002 / adma.202004207
[ad_2]
Source link
