artificial intelligence News - Page 63 of 114 - CNX Software

July 16, 2021 by Jean-Luc Aufranc (CNXSoft) - No Comments

Innatera neuromorphic AI accelerator for spiking neural networks (SNN) enables sub-mW AI inference

Most AI accelerators currently rely on CNN (convolutional neural network) to perform AI inference in a much faster and efficient way than on CPU cores, or even GPUs. But there’s another type of neural network, namely spiking neural networks (SNN) that uses the timing of spikes in an electrical signal to perform pattern recognition tasks in a way similar to neurons in the brain. The claims in terms of efficiency are quite unbelievable, with up to 10,000 times more performance per watts than in microprocessor and digital accelerometer, 500 times lower energy, and 100 times shorter latency. Several companies are working on neuromorphic AI accelerators for spiking neural networks, with notably Prophesee focusing on image processing, and Innatera that is working on an ultra-low-power AI accelerator handling audio, health, and radar for sound and speech recognition, vital signs monitoring, elderly person fall sensors, etc… Innatera recently provided additional information about […]

July 14, 2021July 14, 2021 by Jean-Luc Aufranc (CNXSoft) - 15 Comments

MAIX-II A AI camera board combines Allwinner R329 smart audio processor with USB-C camera

Earlier this year, we wrote about Sipeed MAIX-II Dock AIoT vision devkit with an Allwinner V831 camera processor with a small 200 MOPS NPU, an Omnivision SP2305 2MP camera sensor, and a 1.3-inch display. But for some reason, which could be supply issues, Sipeed has designed a much different variant called MAIX-II A with a board based on Allwinner R329 smart audio processor, a 720p30 USB camera module, and a 1.5-inch display. MAIX-II A board specifications: Main M.2 module – Maix-II A module with Allwinner R329 dual-core Cortex-A53 processor @ 1.5 GHz, 256MB DDR3 on-chip, a dual-core HIFI4 DSP @ 400 MHz, and Arm China AIPU AI accelerator for up to 256 MOPS, plus Wi-Fi & BLE and a footprint for an SPI Flash. Storage – MicroSD card socket Display – 1.5-inch LCD display with 240×240 resolution Audio – Dual microphones, 3W speakers Camera – 720p USB-C camera module based […]

July 14, 2021January 9, 2023 by Jean-Luc Aufranc (CNXSoft) - 9 Comments

XUAN-Bike self-balancing, self-riding bicycle relies on flywheel, 22 TOPS Huawei Ascend A310 AI processor

After Huawei engineer Peng Zhihui Jun fell off this bicycle, he decided he should create a self-balancing, self-riding bicycle, and ultimately this gave birth to the XUAN-Bike, with XUAN standing for eXtremely, Unnatural Auto-Navigation, and also happening to be an old Chinese name for cars. The bicycle relies on a flywheel and a control board with ESP32 and MPU6050 IMU for stabilization connected over a CAN bus to the motors, as well as Atlas 200 DK AI Developer Kit equipped with the 22 TOPS Huawei Ascend A310 AI processor consuming under 8W connected to a 3D depth camera and motor for self-riding. It’s not the first time we see this type of bicycle or even motorcycle, but the XUAN-Bike design is also fairly well-documented with the hardware design (electronics + 3D Fusion360 CAD files) and some documentation in Chinese uploaded to Github. The software part has not been released so […]

July 13, 2021July 13, 2021 by Jean-Luc Aufranc (CNXSoft) - 19 Comments

Station M2 business-card sized Android 11 mini PC, also supports Ubuntu & Buildroot

After introducing Station P2 Rockchip RK3568 mini PC in March of this year, Firefly has now launched another, cheaper model with the ultra-thin Station M2 computer based on the company’s ROC-RK3566-PC single board computer equipped with Rockchip RK3566 SoC. Station M2 is only slightly larger than a business card, but packs up to 8GB RAM, M.2 SSD storage, HDMI 2.0, Gigabit Ethernet, and USB 3.0/2.0 ports. Station M2 specifications: SoC – Rockchip RK3566 with a quad-core Cortex-A55 processor @ up to 1.8GHz. Arm Mali-G52 2EE GPU with support for OpenGL ES 1.1/2.0/3.2. OpenCL 2.0. Vulkan 1.1, 0.8 TOPS AI accelerator, 4K H.265/H.265/VP9 video decoder, 1080p100 H.265/H.264 video encoder. System Memory – 2GB or 4GB LPDDR4 (8GB optional) Storage – 32GB or 64GB (128GB eMMC optional), M.2 PCIe 2.0 socket for 2242 NVMe SSD, MicroSD card socket Video Output – 1x HDMI port up to 4Kp60 Audio – 3.5mm headphone jack, […]

July 9, 2021July 9, 2021 by Jean-Luc Aufranc (CNXSoft) - 1 Comment

Embedded development board features Microchip PolarFire RISC-V FPGA SoC

PolarFire RISC-V FPGA SoC development board

Microchip/MicroSemi first introduced PolarFire RISC-V FPGA SoC at the end of 2018, with the chip being like the RISC-V equivalent of Xilinx Zynq Ultrascale+ Arm & FPGA MPSoC. The following year, ARIES Embedded unveiled the ARIES M100PF system-on-module and evaluation board, before Microchip launched PolarFire SoC Icicle 64-bit RISC-V and FPGA development board, followed by the more compact PolarBerry SBC in 2020. There’s now at least a fourth platform based on PolarFire SoC with Aldec TySOM-M-MPFS250 embedded development board. Aldec TySOM-M-MPFS250 specifications: SoC – Microchip PolarFire MPFS250T-FCG1152 SoC with 4x SiFive U54 RV64GC application cores (similar to Cortex-A35 performance), 1x SiFive E51 RV64IMAC monitor core, FPGA fabric with 254K logic cells, 17.6 Mb RAM System Memory 2GB (16Gbit) 32-bit DDR4 for the FPGA 2GB (16Gbit) 36-bit RAM with ECC for the RISC-V cores (aka MSS = Microprocessor Subsystem) Storage – MicroSD card socket, eMMC flash, SPI flash, 64 Kbit […]

July 9, 2021July 30, 2021 by Jean-Luc Aufranc (CNXSoft) - 20 Comments

Kendryte K510 tri-core RISC-V AI processor deliver up to 3 TOPS

Kendryte K510 is a 64-bit tri-core RISC-V processor clocked at up to 800 MHz with AI accelerators that succeed the 400 MHz Kendryte K210 dual-core RISC-V AI processor released a few years ago first in Kendryte KD233 board, and then boards like Maxduino or Grove AI HAT conveniently programmable with Arduino or Micropython. Canaan formally announced the processor yesterday at the 2021 World Artificial Intelligence Conference claiming K510 had three times the performance of K210 making it suitable for UAV high-definition aerial photography, high-definition panoramic video conferences, robotics, STEAM education, driver assistance scenarios, and industrial and professional cameras. The press release did not have much information, but multiple sources provided additional details to CNX Software, so we have Kendryte K510 specifications: Processor – 2x 64-bit RISC-V processor @ 800 MHz, and 1x 64-bit RISC-V core @ 800 MHz with DSP extension AI subsystem with 3 TOPS in total KPU: General […]

July 6, 2021July 6, 2021 by Jean-Luc Aufranc (CNXSoft) - 3 Comments

AIfES for Arduino high-efficiency AI framework for microcontrollers becomes open source

AIfES (AI for Embedded Systems) is a standalone, high-efficiency, AI framework, which allows the Fraunhofer Institute for Microelectronic Circuits and Systems, or Fraunhofer IMS for short, to train and run machine learning algorithms on resource-constrained microcontrollers. So far the framework was closed-source and only used internally by Fraunhofer IMS, but following a collaboration with Arduino, AIfES for Arduino is now open-source and free to use for non-commercial projects. The framework has been optimized to allow 8-bit microcontrollers such as the one found in Arduino Uno to implement an Artificial Neural Network (ANN) that can be trained in moderate time. That means offline inference and training on small self-learning battery-powered devices is possible with AIfES without relying on the cloud or other devices. The library implements Feedforward Neural Networks (FNN) that can be freely parameterized, trained, modified, or reloaded at runtime. Programmed in C language, AIfES uses only standard libraries based […]

July 1, 2021July 1, 2021 by Jean-Luc Aufranc (CNXSoft) - No Comments

Vecow ABP-3000 AI Edge gateway combines Hailo-8 AI accelerator with Intel Whiskey Lake processor

We first discovered Hailo-8 AI accelerator with claims of up to 26 TOPS performance and 3TOPS/W efficiency in October 2020. Since then, we’ve seen several integrate an Hailo-8 M.2 module into their design including EdgeTuring Edge AI camera and Vecow VAC-1000 gateway with a 24-core Foxconn processor. Vecow has now integrated the Hailo-8 AI accelerator into another gateway, but instead of relying on an Arm processor, the Vecow ABP-3000 AI computing system features an 8th generation Intel Core Whiskey Lake processor. Vecow ABP-3000 specifications: SoC – Intel Core i7-8665UE or i3-8145UE quad-core Whiskey Lake processor with Intel UHD Graphics 620; 15W TDP System Memory – 2x DDR4 2400MHz SO-DIMM, up to 64GB Storage – 1x M.2 Key B Socket (PCIe x2/SATA) AI Accelerator – Hailo-8 AI Processor, up to 26 TOPS with TensorFlow, ONNX frameworks support System IO chip – IT8786E Video Output – 2x DisplayPort up to 4096 x […]