With all the talk and focus on artificial intelligence (AI), it may surprise you that even the most powerful computers are no match for the human brain when it comes to pattern recognition, risk management, and other complex tasks. Science Daily brought this interesting information to our attention in their article, “All-optical neural network for deep learning.”
Recent advances in optical neural networks are working hard to close that gap by simulating the way neurons respond in the human brain. Researchers have demonstrated a first-of-its-kind multi-layer all-optical artificial neural network. In the past, this type of AI can tackle complex problems, but require extensive computational resources that are both time-consuming and require extensive energy.
“Our all-optical scheme could enable a neural network that performs optical parallel computation at the speed of light while consuming little energy,” said Junwei Liu, a member of the research team from The Hong Kong University of Science and Technology. “Large-scale, all-optical neural networks could be used for applications ranging from image recognition to scientific research.”
Melody K. Smith
Sponsored by Data Harmony, a unit of Access Innovations, the world leader in indexing and making content findable.