Even the most powerful computers are still no match for the human brain when it comes to pattern recognition, risk management, and other similarly complex tasks. Recent advances in optical neural networks, however, are closing that gap by simulating the way neurons respond in the human brain.
In a key step toward making large-scale optical neural networks practical, researchers have demonstrated a first-of-its-kind multilayer all-optical artificial neural network. Generally, this type of artificial intelligence can tackle complex problems that are impossible with traditional computational approaches, but current designs require extensive computational resources that are both time-consuming and energy intensive. For this reason, there is great interest developing practical optical artificial neural networks, which are faster and consume less power than those based on traditional computers.
In Optica, The Optical Society’s journal for high-impact research, researchers from The Hong Kong University of Science and Technology, Hong Kong detail their two-layer all-optical neural network and successfully apply it to a complex classification task.
“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. “Large-scale, all-optical neural networks could be used for applications ranging from image recognition to scientific research.”
Building an all-optical network
In conventional hybrid optical neural networks, optical components are typically used for linear operations while nonlinear activation functions—the functions that simulate the way neurons in the human brain respond—are usually implemented electronically because nonlinear optics typically require high-power lasers that are difficult to implement in an optical neural network.
To overcome this challenge, the researchers used cold atoms with electromagnetically induced transparency to perform nonlinear functions. “This light-induced effect can be achieved with very weak laser power,” said Shengwang Du, a member of the research team. “Because this effect is based on nonlinear quantum interference, it might be possible to extend our system into a quantum neural network that could solve problems intractable by classical methods.”
To confirm the capability and feasibility of the new approach, the researchers constructed a two-layer fully-connected all optical neural network with 16 inputs and two outputs. The researchers used their all-optical network to classify the order and disorder phases of the Ising model, a statistical model of magnetism. The results showed that the all-optical neural network was as accurate as a well-trained computer-based neural network.
Optical neural networks at larger scales
The researchers plan to expand the all-optical approach to large-scale all-optical deep neural networks with complex architectures designed for specific practical applications such as image recognition. This will help demonstrate that the scheme works at larger scales.
“Although our work is a proof-of-principle demonstration, it shows that it may become possible in the future to develop optical versions of artificial intelligence,” said Du. “The next generation of artificial intelligence hardware will be intrinsically much faster and exhibit lower power consumption compared to today’s computer-based artificial intelligence,” added Liu.
The Latest on: Optical artificial neural networks
via Google News
The Latest on: Optical artificial neural networks
- Neural Network Keeps It Lighton October 3, 2020 at 5:00 pm
The artificial neurons look for inputs to ... There’s been a lot of work done lately on both neural networks and optical computing. Perhaps this fusion will advance both arts.
- NTT Research and University of Notre Dame Collaborate to Explore Continuous-Time Analog Computingon September 26, 2020 at 7:27 am
NTT Research PHI Lab enters joint research agreement with University of Notre Dame in the area of continuous-time analog computing.
- Asus AIoT builds new smart manufacturing solutions to promote industrial upgradeson September 24, 2020 at 6:55 pm
With the advent of the AIoT era, Asus has embraced new technologies and methods to develop advanced manufacturing capabilities. At the end of 2019, Asus expanded the company's AIoT business unit to be ...
- AI: Metalens-Array-Based High-Dimensional and Multi-Photon Quantum Sourceon September 6, 2020 at 12:40 am
The interference experiment obtained a fidelity of nearly 98.4%, which confirmed the feasibility of this high-dimensional quantum entangled optical chip (optical ... machine learning, artificial ...
- Marios Mattheakison August 25, 2020 at 5:00 pm
His primary area of research is the design of artificial neural networks and neuromorphic architectures with implementations in physics, engineering, and beyond. Moreover, he is interested in ...
- Ultrafast machine visionon August 17, 2020 at 7:33 am
Thomas Mueller and colleagues now demonstrate an image sensor that itself can constitute an artificial neural network, simultaneously sensing and processing optical images in real time without latency ...
- Artificial Neural Networkson September 17, 2019 at 3:10 pm
An Artificial Neural Network is an approach to modelling the structure and ... text to speech conversion, diagnosis of disease, optical quality control, image processing, and chemical analysis. The ...
- AI Makes Inroads in Physicson June 4, 2018 at 12:06 pm
2018 APS April Meeting, Columbus, Ohio — These days, artificial intelligence (AI ... Each layer of a deep neural network recognizes increasingly complex features in images (from left to right).
- Spiking activity propagation in neuronal networks: reconciling different perspectives on neural codingon September 1, 2010 at 5:00 am
Controlled stimulation of appropriately selected neural networks in vivo using either electrical or optical methods to ... experiments using simple (artificial) or natural sensory stimuli are ...
- Robots tricked by optical illusionson October 5, 2007 at 5:00 am
To address the question of why humans see illusions, researchers at the UCL Institute of Ophthalmology used artificial neural networks -- effectively virtual toy robots with miniature virtual ...
via Bing News