artificial intelligence News - Page 79 of 98 - CNX Software

July 3, 2019July 3, 2019 by Stephen Vicinanza - 1 Comment

GAPPoc AI development boards based on the GAP8 RISC-V Chip

GreenWaves has developed a development board based on the GAP8 chip which can be evaluated from a GAPuino board, a generic board that can run off a low power external power source or USB and is compatible with the Arduino ecosystem. Recently the company moved beyond the generic board to the GAPPoc, platform which stands for GAP8 Proof of Concept. The GAPPoc is focused on a class of applications which can be embedded on a single board and able to carry hardware such as crystal or external memory, sensors, a radio fit, and a battery. The board will be geared towards a set of low power functions for a particular class of applications. This is a family of boards designed to increase the range of abilities in edge Artificial Intelligence. At this time there is only a single board with a platform to enhance AI, targeting Computer Vision in the […]

July 2, 2019 by Jean-Luc Aufranc (CNXSoft) - No Comments

S+ Camera Basic Combines Raspberry Pi 3 Board and LTE Shield for Edge Applications

Soracom is a company that provides global IoT network cellular connectivity for businesses in smart IoT agriculture, energy, consumer, manufacturing, transportation, and medical industries, and even provides free IoT SIM cards for evaluation (US/Canada only). The company has just announced the S+ Camera on its Japanese blog. The camera looks to features several off-the-shelf components including a Raspberry Pi 3 board and SixFab Raspberry Pi 3G-4G/LTE Base Shield V2 connecting to Soramcom network. It’s a little confusing as to why a cellular IoT company would develop an LTE camera since streaming video requires bitrates not normally associated with IoT. The blog post does provide a few more details however, as S + Camera is said to run SORACOM Mosaic software which enables “algorithms for edge processing cameras and management and operation of cameras”. That means it’s quite possible the video will not be streamed, but edge processing/computing usually means AI is […]

July 1, 2019October 20, 2019 by Jean-Luc Aufranc (CNXSoft) - 15 Comments

Khadas VIM3 Review – Part 1: Kit Unboxing and Assembly

We started to read about Khadas VIM3 in May of this year as an Amlogic S922X development board with an M.2 socket for NVMe SSD, and 802.11ac WiFi 5 & Bluetooth 5.0 wireless module. Eventually, Shenzhen Wesion decided to change the processor to Amlogic A311D before the launch last month, since it does not cost much more, but includes a 5.0 TOPS neural processing engine. The company has sent me a Khadas VIM3 kit for evaluation and review. Before going through the software part, and especially the tools for the NPU which will be one of the highlights of the board, I’ll check out what I received today, and show how to assemble the kit. Khadas VIM3 Kit Unboxing The package is rather boring… But what’s really important is what’s inside… We’ve got an enclosure, a smaller package with the board itself, a USB-C power supply, a thermal pad + […]

July 1, 2019December 4, 2019 by Jean-Luc Aufranc (CNXSoft) - 4 Comments

96Boards RK1808 & RK3399Pro SoM & Devkit Now Available for Purchase

Back in April, we covered the very first 96Boards SoM’s (Systems-on-Module) which were based on Rockchip RK3399Pro or RK1808 processors, and targeted applications leveraging artificial intelligence acceleration. There were not quite available at the time, but Seeed Studio now has both BeiQi modules for pre-order for $119 and $59 respectively, while the carrier board goes with $125 with antennas, and power supply. Note that the RK3399Pro SoM and the carrier board are basically available now with shipping schedule for July 4th, but you’d had to wait until the end of the month for the RK1808 module. BeiQi RK1808 AIoT 96Boards Compute SoM Module specifications: SoC – Rockchip RK1808 dual-core Arm Cortex-A35 processor @ 1.6 GHz with NPU supporting 8-bit/16-bit operations up to 3.0 TOPS, TensorFlow and Caffe frameworks; 22nm FD-SOI process System Memory – 1GB LPDDR3 (I also read “4GB LPDRR3” (sic.) in other places, but the capacity is likely […]

June 27, 2019 by Jean-Luc Aufranc (CNXSoft) - 4 Comments

MediaTek Helio P65 Octa-core Processor Combines Cortex-A75/A55 Cores with Arm Mali-G52 GPU

MediaTek Helio P65 is a mainstream’s octa-core processor with two Arm Cortex-A75 clocked at up to 2.0 GHz and six Cortex-A55 cores combined with an Arm Mali-G52 2EEMC2 GPU. What does 2EEMC2 mean you may ask? Well, I have absolutely no idea either, and MediaTek did not bother expanding on the subject. Nevertheless, Helio P65 is said to deliver 25% performance improvement over “competitor alternatives that use older generation cores”, and twice the AI performance over previous generation mainstream Helio series, and up to 30% faster performance versus direct competitor SoCs in AI-camera tasks such as object recognition (Google Lens). The processor also implements VoW (Voice on Wakeup) capability which the company claims “optimizes platform size and power use”, and separates the audio channels for voice commands and calls from media and games in order to deliver better audio quality. MediaTek Helio P65 specifications: Processor – 6x Arm Cortex-A55, 2x […]

June 25, 2019June 25, 2019 by Jean-Luc Aufranc (CNXSoft) - 29 Comments

Khadas VIM3 SBC Launched with Amlogic A311D Processor, 5 TOPS NPU

We’ve previously written about Khadas VIM3 Amlogic S922X development board and revealed the price tag for VIM3 Basic ($69.99) and VIM3 Pro ($99.99) with a launch date announced for June 24. As time has passed, this has become “fake news” except for the launch date, as Khadas VIM3 SBC has indeed launched but for $99.99 (Basic) and $139.99 (Pro). What’s going on? Why the large price increase? That’s because Khadas team has decided to provide a more powerful platform to the community, and replace Amlogic S922X processor with Amlogic A311D processor boasting higher clock speeds and a 5.0 TOPS NPU. Another version may also become available later on with the soon-to-be-released Amlogic S922X-B processor whose Cortex-A73 cores are clocked at up to 2.2 GHz, instead of 1.7 GHz for the original Amlogic S922X processor that will be referred to Amlogic S922X-A in the future. New Khadas VIM3 SBC specifications: SoC […]

June 11, 2019June 13, 2019 by Jean-Luc Aufranc (CNXSoft) - 1 Comment

AAEON AI Core XP4/XP8 PCIe Card Combines up to 8 Myriad X VPU’s

Movidius Myriad X is Intel’s latest vision processing unit (VPU) first unveiled in 2017, and available for evaluation in Intel Neural Compute Stick 2 since the end of 2018. Later on, AAEON also launched their own AI Core XM2280 M.2 card equipped with two Myriad X 2485 VPU’s and capable of up to 200 fps (160 fps typical) inferences, thanks to over 2 TOPS of deep neural network (DNN) performance. But what if you need even more performance? The company has now launched AI Core XP4/XP8 card with either two or four AI Core XM2280 M.2 cards that can be connected into any computer or workstation with a PCIe x4 slot. AAEON AI Core XP4/XP8 specifications: 4x M.2 sockets for 2x or 4x M.2 2280 M-key cards with 2x Myriad X VPU’s and 2x 4Gbit LPDDR4x memory each Asmedia PCIe switch Cooling – Fan heatsink PCIe x4 standard full-length low […]

June 11, 2019 by Jean-Luc Aufranc (CNXSoft) - 6 Comments

$69.99 Gyrfalcon 2803 Plai Plug Delivers 24 TOPS per Watt

Last year we covered an alternative to Intel Movidius Neural Compute Stick with Orange Pi AI Stick 2801 powered by Gyrfalcon Lightspeeur 2801S neural processor, and delivering up to 5.6 TOPS, or 2.8TOPS @ 300mW for $69. Since then Gyrfalcon introduced Lightspeeur 2803(S) AI accelerator delivering up to 24 TOPS, or 16.8 TOPS @ 700 mW. We’ve recently seen the new neural processor will be integrated into SolidRun i.MX 8M Mini & Nano systems-on-module, and today the company published a press release to announce their latest 2803 Plai Plug providing an upgrade to their existing 2801 Plai Plug (Orange Pi AI Stick 2801) for about the same $69.99 price tag. Gyrfalcon 2803 Plai Plug preliminary specifications: AI Accelerator – Gyrfalcon Lightspeeur 2803S with 2-dimensional Matrix Processing Engine (MPE) and AI Processing in Memory (APiM) Storage – eMMC flash Host interface – USB 3.0 port Power Consumption – 700mW at 16.8 […]