A low power programmable network for optical AI
Researchers in Switzerland have developed a low power non-linear neural network in an optical fibre.
A team at EPFL developed an energy-efficient method for performing nonlinear computations for optical AI. The new approach involves encoding data in the spatial modulation of a low-power laser beam where the beam reflects back on itself several times, leading to a nonlinear multiplication.
While digital neural networks can easily perform nonlinear transformations with transistors, in optical systems, this step requires very powerful lasers.
Instead, the programmable framework developed at EPFL, called nonlinear processing with only linear optics (nPOLO), uses a low-power continuous-wave laser and diffractive layers and the nPOLO programmable framework enables simultaneous linear and nonlinear operations within the optical domain. The team are also developing a compiler to convert digital data to data suitable for the optical AI system.
“In order to classify data in a neural network, each node, or ‘neuron’, must make a ‘decision’ to fire or not based on weighted input data. This decision leads to what is known as a nonlinear transformation of the data, meaning the output is not directly proportional to the input,” says Christophe Moser, head of the Laboratory of Applied Photonics Devices in EPFL’s School of Engineering.
“Our method is up to 1,000 times more power-efficient than state-of-the-art deep digital networks, making it a promising platform for realizing optical neural networks,” said Demetri Psaltis, director of the Optics Laboratory.
“Our image classification experiments on three different datasets showed that our method is scalable, and up to 1,000 times more power-efficient than state-of-the-art deep digital networks, making it a promising platform for realizing optical neural networks,” said Psaltis.
The team encoded the pixels of an image spatially on the surface of a low-power laser beam. By performing this encoding twice, via adjustment of the trajectory of the beam in the encoder, the pixels are multiplied by themselves, i.e., squared. Since squaring is a non-linear transformation, this structural modification achieves the non-linearity essential to neural network calculations, at a fraction of the energy cost. This encoding can be carried out two, three or even ten times, increasing the non-linearity of the transformation and the precision of the calculation.able
“We estimate that using our system, the energy required to optically compute a multiplication is eight orders of magnitude less than that required for an electronic system,” said Psaltis.
Moser and Psaltis emphasize that the scalability of their low-energy approach is a major advantage for optical AI systems, as the ultimate goal would be to use hybrid electronic-optical systems to mitigate the energy consumption of digital neural networks.
However, further engineering research is needed to achieve such scale-up. For example, because optical AI systems use different hardware than electronic systems, a next step that the researchers are already working on is developing a compiler to translate digital data into code that optical systems can use.
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
