CSEM engineers have developed an integrated circuit that can carry out complicated artificial-intelligence operations like face, voice and gesture recognition and cardiac monitoring. Powered by either a tiny battery or a solar panel, it processes data at the edge and can be configured for use in just about any type of application.
AI is used in an array of extremely useful applications, such as predicting a machine’s lifetime through its vibrations, monitoring the cardiac activity of patients and incorporating facial recognition capabilities into video surveillance systems. The downside is that AI-based technology generally requires a lot of power and, in most cases, must be permanently connected to the cloud, raising issues related to data protection, IT security and energy use.
CSEM engineers may have found a way to get around those issues, thanks to a new system-on-chip they have developed. It runs on a tiny battery or a small solar cell and executes AI operations at the edge – i.e., locally on the chip rather than in the cloud. What’s more, their system is fully modular and can be tailored to any application where real-time signal and image processing is required, especially when sensitive data are involved. The engineers will present their device at the prestigious 2021 VLSI Circuits Symposium in Kyoto this June.
The CSEM system-on-chip works through an entirely new signal processing architecture that minimizes the amount of power needed. It consists of an ASIC chip with a RISC-V processor (also developed at CSEM) and two tightly coupled machine-learning accelerators: one for face detection, for example, and one for classification. The first is a binary decision tree (BDT) engine that can perform simple tasks but cannot carry out recognition operations.
“When our system is used in facial recognition applications, for example, the first accelerator will answer preliminary questions like: Are there people in the images? And if so, are their faces visible?”, says Stéphane Emery, head of system-on-chip research at CSEM. “If our system is used in voice recognition, the first accelerator will determine whether noise is present and if that noise corresponds to human voices. But it can’t make out specific voices or words – that’s where the second accelerator comes in.”
The second accelerator is a convolutional neural network (CNN) engine that can perform these more complicated tasks – recognizing individual faces and detecting specific words – but it also consumes more energy. This two-tiered data processing approach drastically reduces the system’s power requirement, since most of the time only the first accelerator is running.
As part of their research, the engineers enhanced the performance of the accelerators themselves, making them adaptable to any application where time-based signal and image processing is needed.
“Our system works in basically the same way regardless of the application,” says Emery. “We just have to reconfigure the various layers of our CNN engine.”
The CSEM innovation opens the door to an entirely new generation of devices with processors that can run independently for over a year. It also sharply reduces the installation and maintenance costs for such devices, and enables them to be used in places where it would be hard to change the battery.
Original Article: AI SYSTEM-ON-CHIP RUNS ON SOLAR POWER
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
- NSWC Crane, IU, Notre Dame, and Purdue team up to provide Trusted AI workforce development and researchon June 30, 2021 at 12:01 pm
CRANE – Naval Surface Warfare Center, Crane Division (NSWC Crane) is teaming up with state academic institutions Indiana University (IU), The University of Notre Dame, and Purdue University to develop ...
- Volvo XC90 electric SUV will feature LiDAR and AI “super computer”on June 29, 2021 at 6:57 pm
The flagship electric SUV from Swedish automotive giant Volvo Cars will boast as standard state-of-the-art LiDAR technology which will be powered by an autonomous driving super computer. The ...
- Skullcandy and Bragi Partner to Enable Hands-Free Audio Experiences Via Intuitive Voice Commandson June 29, 2021 at 5:07 am
Skullcandy Inc., the #1 selling North American brand in stereo headphones 1 and true wireless earbuds 2 under $100, announced today a partnership with Bragi, the inventor and largest intellectual ...
- OnePlus Nord 2 Spotted On AI Benchmark With Dimensity 1200 SoC, 8GB RAMon June 28, 2021 at 5:31 am
An AI benchmark listing has revealed the processor ... The Dimensity 1200 is the Taiwanese company’s most advanced smartphone system-on-a-chip (SoC). So it perfectly fits the billing for a ...
- Qualcomm Snapdragon 888 Plus 5G clocks up to 3.0GHz, brings 20% AI performance booston June 28, 2021 at 3:16 am
The Snapdragon 888 Plus is manufactured using a 5nm process and shares many features and specs with its predecessor.
Go deeper with Google Headlines on:
Go deeper with Bing News on:
Convolutional neural network
- Video Swin Transformer Improves Speed-Accuracy Trade-offs, Achieves SOTA Results on Video Recognition Benchmarkson July 1, 2021 at 9:00 am
Introduced in 2020, the Vision Transformer (ViT) globally connects patches across spatial and temporal dimensions, and has largely replaced convolution neural networks (CNNs) as the modelling choice ...
- Here’s how deep learning helps computers detect objectson June 28, 2021 at 8:30 am
Today, many applications use object-detection networks as one of their main components. It’s in your phone, computer, car, camera, and more.
- Convolutional neural network-based ensemble methods to recognize Bangla handwritten characteron June 28, 2021 at 4:47 am
The proposed methods of this study are divided into three phases. In the first phase, seven convolutional neural networks i.e., CNN-based architectures are created. After that, the best performing CNN ...
- New Part Day: The RISC-V Chip With Built-In Neural Networkson June 25, 2021 at 5:00 pm
It’s a dual-core, RISC-V chip running at 400MHz. There’s 6 MB of SRAM on the CPU, and there’s 2MB for convolutional neural network acceleration. There is, apparently, WiFi on some versions.
- MRI images reconstructed by artificial intelligence could accelerate and better guide radiotherapyon June 25, 2021 at 7:24 am
An artificial intelligence (AI) that reconstructs MRI images of moving tumors can do so in seconds, offering a significant improvement on current methods to optimize radiotherapy treatment in the ...