UCLA engineers have made major improvements on their design of an optical neural network –a device inspired by how the human brain works – that can identify objects or process information at the speed of light.
The development could lead to intelligent camera systems that figure out what they are seeing simply by the patterns of light that run through a 3D engineered material structure. Their new design takes advantage of the parallelization and scalability of optical-based computational systems.
For example, such systems could be incorporated into self-driving cars or robots, helping them make near-instantaneous decisions faster and using less power than computer-based systems that need additional time to identify an object after it’s been seen.
The technology was first introduced by the UCLA group in 2018. The system uses a series of 3D-printed wafers or layers with uneven surfaces that transmit or reflect incoming light – they’re reminiscent in look and effect to frosted glass. These layers have tens of thousands of pixel points – essentially these are artificial neurons that form an engineered volume of material that computes all-optically. Each object will have a unique light pathway through the 3D fabricated layers.
Behind those layers are several light detectors, each previously assigned in a computer to deduce what the input object is by where the most light ends up after traveling through the layers.
For example, if it’s trained to figure out handwritten digits, then the detector programmed to identify a “5” will see the most of the light hit that detector after the image of a “5” has traveled through the layers.
In this recent study, published in the open access journal Advanced Photonics, the UCLA researchers have significantly increased the system’s accuracy by adding a second set of detectors to the system, and therefore each object type is now represented with two detectors rather than one. The researchers aimed to increase the signal difference between a detector pair assigned to an object type. Intuitively, this is similar to weighing two stones simultaneously with the left and right hands – it is easier this way to differentiate if they are of similar weight or have different weights.
This differential detection scheme helped UCLA researchers improve their prediction accuracy for unknown objects that were seen by their optical neural network.
In this recent study, published in the open access journal Advanced Photonics, the UCLA researchers have significantly increased the system’s accuracy by adding a second set of detectors to the system, and therefore each object type is now represented with two detectors rather than one. The researchers aimed to increase the signal difference between a detector pair assigned to an object type. Intuitively, this is similar to weighing two stones simultaneously with the left and right hands – it is easier this way to differentiate if they are of similar weight or have different weights.
This differential detection scheme helped UCLA researchers improve their prediction accuracy for unknown objects that were seen by their optical neural network.
“Such a system performs machine-learning tasks with light-matter interaction and optical diffraction inside a 3D fabricated material structure, at the speed of light and without the need for extensive power, except the illumination light and a simple detector circuitry,” said Aydogan Ozcan, Chancellor’s Professor of Electrical and Computer Engineering and the principal investigator on the research. “This advance could enable task-specific smart cameras that perform computation on a scene using only photons and light-matter interaction, making it extremely fast and power efficient.”
The researchers tested their system’s accuracy using image datasets of hand-written digits, items of clothing, and a broader set of various vehicles and animals known as the CIFAR-10 image dataset. They found image recognition accuracy rates of 98.6%, 91.1% and 51.4% respectively.
Those results compare very favorably to earlier generations of all-electronic deep neural nets. While more recent electronic systems have better performance, the researchers suggest that all-optical systems have advantages in inference speed, low-power, and can be scaled up to accommodate and identify many more objects in parallel.
Learn more: Optical neural network could lead to intelligent cameras
The Latest on: Intelligent cameras
[google_news title=”” keyword=”intelligent cameras” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Intelligent cameras
- Opal Tadpole webcam: A gorgeous design with a Sony mirrorless cameraon May 1, 2024 at 11:11 am
The Opal Tadpole is an incredibly capable webcam that is well-engineered and beautifully designed. The video quality is respectable, but my lasting impression of the Tadpole was not to do with the ...
- myQ Smart Indoor Camera Launchedon May 1, 2024 at 7:00 am
A smart garage door controller is essential for today's smart home with a garage. And pairing it with your home security system or security cameras is critical to creating a secure home security ...
- myQ Expands Ecosystem with Launch of First Smart Indoor Cameraon May 1, 2024 at 6:18 am
The myQ Smart Indoor Camera is the latest evolution in the myQ Smart Access Ecosystem from Chamberlain Group, the global leader in intelligent access. With the new myQ Smart Indoor Camera, you'll be ...
- Neusoft Reach and Ambarella Forge Strategic Partnership to Drive Advancements in Autonomous Driving and Intelligent Automotive Technologyon April 30, 2024 at 4:00 am
Photo: From left to right, Yongfeng Wang, chairman of Neusoft Reach; Wei Lius, deputy general manager of Neusoft Reach; Nick Kong, senior director of Greater China business development at Ambarella; ...
- Neusoft Launches OneCoreGo® Global In-Vehicle Intelligent Mobility Solutions 5.0on April 30, 2024 at 1:56 am
Recently, at Auto China 2024, Neusoft Corporation (Neusoft, SSE:600718) launched OneCoreGo® Global In-Vehicle Intelligent Mobility Solutions 5.0, showcasing its innovative achievements in the AI+ ...
- GigE Camera Market Poised for Remarkable Growth, Predicted CAGR of 9.1% Leading to US$ 5.8 Billion Projection by 2032on April 29, 2024 at 7:44 pm
The global GigE camera market is expected to grow at a CAGR of 9.1% from 2022 to 2032, reaching US$ 5.8 billion. It is expected to be worth US$ 3.5 billion in 2022. Sales of GigE cameras are projected ...
- Meet the New TR315 and TR335 PTZ Cameras from AVeron April 29, 2024 at 5:30 am
Designed to enhance performance from corporate meetings and educational seminars to live performances and worship services.
- This artificially intelligent pin wants to free you from your phoneon April 28, 2024 at 6:00 am
While the AI Pin was occasionally useful and impressive, it was wrong, unhelpful or inefficient enough times to drive me back to my phone ...
- No cameras allowed: Meet the sketch artists bringing color to the Supreme Courton April 25, 2024 at 3:23 pm
Those inside the Supreme Court would have to rely strictly on their visual memory of oral arguments – since photography and video are prohibited while court is in session – were it not for the veteran ...
- Intelligent vision ecosystem tackles design complexityon April 25, 2024 at 7:56 am
Arrow Electronics launches an intelligent vision ecosystem, leveraging the onsemi Imager Access System module standard to reduce design complexity.
via Bing News