Carding 4 Carders
Professional
Oxford scientists have shown how light chips are changing the AI world.
A team of scientists from the University of Oxford, in collaboration with partners from Germany and the UK, has developed a new type of artificial intelligence hardware that uses light to process three-dimensional (3D) data. Based on integrated photonic-electronic chips, the new device can perform complex calculations in parallel, using different wavelengths and radio frequencies of light. Scientists claim that their hardware can speed up data processing for artificial intelligence tasks several times.
The study, published in the journal Nature Photonics, addresses the challenge of meeting the growing demand for computing power from modern artificial intelligence applications. The team says that using light instead of electronics offers a new way of computing that can overcome this barrier.
In their latest work, the scientists added another measure of parallelism to their photonic chip, using different radio frequencies of light to encode the data. With much greater speed and accuracy, the chip can process 3D data, such as images or videos.
Dr Bowei Dong, first author of the paper and a researcher in the Department of Materials at the University of Oxford, said:"We found that using radio frequencies to represent data opens up a whole new dimension, enabling ultra-fast parallel processing for new artificial intelligence hardware."
Professor Harish Bhaskaran, head of research and co-founder of Salience Labs, said: "This is an exciting time to conduct research in artificial intelligence hardware, and this work is one example of how we can push the boundaries of what is possible."
A team of scientists from the University of Oxford, in collaboration with partners from Germany and the UK, has developed a new type of artificial intelligence hardware that uses light to process three-dimensional (3D) data. Based on integrated photonic-electronic chips, the new device can perform complex calculations in parallel, using different wavelengths and radio frequencies of light. Scientists claim that their hardware can speed up data processing for artificial intelligence tasks several times.
The study, published in the journal Nature Photonics, addresses the challenge of meeting the growing demand for computing power from modern artificial intelligence applications. The team says that using light instead of electronics offers a new way of computing that can overcome this barrier.
In their latest work, the scientists added another measure of parallelism to their photonic chip, using different radio frequencies of light to encode the data. With much greater speed and accuracy, the chip can process 3D data, such as images or videos.
Dr Bowei Dong, first author of the paper and a researcher in the Department of Materials at the University of Oxford, said:"We found that using radio frequencies to represent data opens up a whole new dimension, enabling ultra-fast parallel processing for new artificial intelligence hardware."
Professor Harish Bhaskaran, head of research and co-founder of Salience Labs, said: "This is an exciting time to conduct research in artificial intelligence hardware, and this work is one example of how we can push the boundaries of what is possible."
