Renesas

davidfitz

Regular
Great find and would love one of our tech experts to review the following to identify if it could be Akida.

Can't access the 'white paper' on the Embedded AI-Accelerator DRP-AI published on 30 June 2021 which may shed a bit more light.

However, I always get excited when the proposed tech appears to have been implemented after the Licencing Agreement was signed.

1646267319314.png
 
  • Like
  • Fire
Reactions: 12 users

hotty4040

Regular
Interesting that syntiant are able to run RNNs on the AI chip, which was something that was asked about Akida in the lastest presentation with Rob and Tony. From my interpretation of the answer they said that it couldn’t so I’m wondering if this is a material issue? Hopefully someone with a bit more nouce can enlighten us. I’m an accountant not a tech guy 😂
Please excuse my ignorance Tech but what is an ( R ) neural network " on chip ". Haven't as yet come across this before ?

I'm from the " old school " of computer thinking :cool::unsure::whistle:

I hope it's not a " spanner in the works " so to speak, ( if you get my drift )

I'm a retired computer engineer, and i can't get my head around this AI palaver, properly, yet, " but " as they say,

"learning all the time " ;)



Akida Ballista

hotty
 
  • Like
Reactions: 5 users

Makeme 2020

Regular

Tata Elxsi and Renesas Establish Next-Generation EV Innovation Center
USA - English​

Focuses on Electric Vehicle System Development and Market Enablement
Tata Elxsi Logo

NEWS PROVIDED BY
Tata Elxsi
Mar 02, 2022, 19:00 ET

SHARE THIS ARTICLE​


BANGALORE, India and TOKYO, March 3, 2022 /PRNewswire/ -- Tata Elxsi, a global leader in design and technology services, and Renesas Electronics Corporation, a premier supplier of advanced semiconductor solutions, announced today their collaboration on a state-of-the-art design center in Bangalore that will develop targeted solutions for electric vehicles (EV). The new Next Generation EV Innovation Center (NEVIC) was opened in January of this year.
Electric Vehicles have become foundational to the new mobility paradigm across the globe. Certain segments, such as two-wheel and light EVs are finding rapid adoption, especially in emerging markets such as India where these segments fit across multiple use cases. To enable this adoption, solutions that can offer key building blocks for scalability and re-usability while delivering reliable performance and offering room for technology customization are critical. These solutions will support creation of quick-to-market solutions and a wide portfolio of products and variants for OEMs and suppliers.
Tata Elxsi and Renesas will bring together their deep domain expertise, intellectual property, and assets to the NEVIC and collaborate to create reference designs and solution accelerators for critical EV subsystems like Battery Management Systems and Motor Control Units, among others. With the electric vehicle market, especially the Light EV segment, at an inflection point, the companies aim to provide key enablers for the market, starting with India and expanding globally to optimize development time and effort.
''We are excited to continue our collaboration with Renesas, a market leader in semiconductors for integrated, sophisticated and reliable solutions for the Electrification domain," said Shaju S, Vice President and Head of Transportation, Tata Elxsi. "Electric vehicles are revolutionizing not only the traditional automotive market but also the mobility and energy ecosystems as a whole. Our customers will undoubtedly benefit from the proven chipsets and support system of Renesas as it will definitely help us in developing cutting edge and futuristic solutions which the industry demands. Markets like India are especially sensitive to cost, and these solutions will help cut down product development risks, costs and greatly improve time-to-market. In addition, we also bring industry-proven solutions and services for productization, testing, calibration and downstream integration, which will benefit customers in rapid NPI and time-to-market. These include eMobility HILS for validation and AUTOSAR suite 4.2.2 and 4.3 for software integration."
''Renesas is pleased to work with Tata Elxsi, a proven leader of design and technology services for the automotive industry," said Taizo Hayashi, Vice President of Automotive New Business Creation Division, Renesas. ''This collaboration demonstrates our commitment to support the 'Make in India' government initiative and we look forward to generating future business growth in India. The NEVIC Solution Center will be a turning point as OEMs and Tier 1s will now have access to secure system solutions and can leverage Tata Elxsi's Electrification expertise for use case specific customizations."
Through NEVIC's product and service offerings, Tata Elxsi and Renesas will support the acceleration of eMobility, particularly the two-wheel and light EV segments, assisting clients in overcoming time to market and technology complexity.
About Tata Elxsi
Incorporated in 1989, Tata Elxsi is amongst the world's leading providers of design and technology services across industries, including Automotive, Media, Communications, Healthcare, and Transportation. Tata Elxsi's 12+ years of deep domain expertise in electrification is complemented by our 30+ years of technology and product development heritage that enable brands to differentiate and win. Tata Elxsi provides integrated offerings – from research and strategy to electronics and mechanical design, software development, validation, and deployment, and is supported by a network of design studios, global development centers, and offices worldwide. These cover the entire spectrum of the EV ecosystem, from the In-Vehicle systems and subsystems to the connectivity, cloud platform and EV infrastructure elements.
For more information, please visit https://www.tataelxsi.com/industrie...ng/next-generation-ev-innovation-center-nevic
About Renesas Electronics Corporation
Renesas Electronics Corporation (TSE: 6723) delivers trusted embedded design innovation with complete semiconductor solutions that enable billions of connected, intelligent devices to enhance the way people work and live. A global leader in microcontrollers, analog, power, and SoC products, Renesas provides comprehensive solutions for a broad range of automotive, industrial, Infrastructure, and IoT applications that help shape a limitless future. Learn more at renesas.com. Follow us on LinkedIn, Facebook, Twitter, YouTube, and Instagram.
Media Contact
 
  • Like
  • Fire
Reactions: 12 users

Makeme 2020

Regular
 
  • Like
  • Thinking
Reactions: 3 users

Makeme 2020

Regular

Renesas Automotive Semiconductors Selected by Honda for ADAS

Renesas R-Car SoC and RH850 MCU to be Used in Honda SENSING System
(Graphic: Business Wire)
(Graphic: Business Wire)
March 03, 2022 08:00 AM Eastern Standard Time
TOKYO--(BUSINESS WIRE)--Renesas Electronics Corporation (TSE:6723), a premier supplier of advanced semiconductor solutions, today announced the expansion of its collaboration with Honda in the field of advanced driver-assistance systems (ADAS).
“Honda is a global innovator in research and development work on safety technologies aimed at the realization of a society with zero traffic collision fatalities”
Tweet this
Honda adopted Renesas’ R-Car automotive system on a chip (SoC) and RH850 automotive MCU for its Honda SENSING Elite system featured in the Legend, which went on sale in March 2021. Honda SENSING Elite incorporates advanced technology that qualifies for Level 3 automated driving (conditional automated driving in limited areas). Now Honda has again selected R-Car and RH850 for use in the Honda SENSING 360 omnidirectional safety and driver assistance system, which builds on the knowledge and expertise gained through research and development work on the earlier technology. The first automobile model equipped with Honda SENSING 360 is scheduled for release in China in 2022, with adoption in a broader range of models to follow.
Furthermore, for the next-generation Honda SENSING 360 system, Honda has selected the R-Car S4 as the main SoC in the electronic control unit (ECU), the core of the ADAS. Through this, Renesas and Honda are expanding their collaboration in the ADAS field to improve safety technologies.
“Renesas is proud to be able to contribute to innovation in Honda’s advanced safety technologies,” said Takeshi Kataoka, Senior Vice President and General Manager of the Automotive Solution Business Unit at Renesas. “Renesas shares with Honda a design philosophy that emphasizes safety and reliability above all, and we plan to further expand our collaboration to bring sophisticated driver-assistance systems to all mass-production models in the near future.”
“Honda is a global innovator in research and development work on safety technologies aimed at the realization of a society with zero traffic collision fatalities,” said Yutaka Tamagawa, Operating Executive and Head, Electronic Control Development Supervisory Unit, Monozukuri Center, Automobile Operations at Honda. “Renesas’ semiconductor devices optimized for automotive applications are extremely reliable, backed by a solid system of software and support, and provide superior power efficiency. The expansion of our collaborative efforts will speed up the development of Honda SENSING and help lead its widespread adoption.”
In the Honda SENSING Elite flagship advanced technology system, the Renesas R-Car automotive SoC processes sensing data from cameras, millimeter-wave radar, and LiDAR as well as data for 3-dimensional high-definition maps and the global navigation satellite system (GNSS). The SoC also monitors the vehicle’s position and the road conditions, and computes route plans in real time. The RH850 automotive control MCU provides support for driving operations and collision avoidance by receiving signals from R-Car and performing advanced control of the accelerator, braking, and steering systems.
The application of Honda SENSING 360 is expected to expand globally, and Renesas’ R-Car is helping to enable omnidirectional safety and driver-assistance systems by 360-degree sensing with processing sensing data from cameras and millimeter-wave radar.
Moving forward, Renesas is committed to working with Honda on the development and widespread adoption of next-generation Honda SENSING systems.
About Renesas Electronics Corporation
Renesas Electronics Corporation (TSE: 6723) delivers trusted embedded design innovation with complete semiconductor solutions that enable billions of connected, intelligent devices to enhance the way people work and live. A global leader in microcontrollers, analog, power, and SoC products, Renesas provides comprehensive solutions for a broad range of automotive, industrial, Infrastructure, and IoT applications that help shape a limitless future. Learn more at renesas.com. Follow us on LinkedIn, Facebook, Twitter, YouTube and Instagram.
 
  • Like
  • Fire
Reactions: 21 users

Learning

Learning to the Top 🕵‍♂️
As we all know, Renesas is one of the two sign's IP agreement. Hence, if Renesas growth, then eventually Brainchip will grow with it.

(25 Feb 2022)

It's great to be a shareholder
 
  • Like
  • Fire
  • Love
Reactions: 13 users

Slade

Top 20
Is Akida part of this?


Renesas Unveils R-Car V4H for Automated Driving Level 2+ / Level 3 to Support High-Volume Vehicle Production in 2024​


New Platform Innovates by Providing a Cutting-Edge Development Environment, Paving the Way to the Software-Defined Car
March 8, 2022
Renesas R-Car V4H SoC for Automated Driving Development of Level 2+ / Level 3
TOKYO, Japan ― Renesas Electronics Corporation (TSE:6723), a premier supplier of advanced semiconductor solutions, today announced the R-Car V4H system on chip (SoC) for central processing in advanced driver-assistance (ADAS) and automated driving (AD) solutions. The R-Car V4H achieves deep learning performance of up to 34 TOPS (Tera Operations Per Second), enabling high-speed image recognition and processing of surrounding objects by automotive cameras, radar, and lidar.
The R-Car V4H enables market-leading performance per watt through a careful combination of best-in-class IP and expert HW optimization. It targets the highest volume zones of automated driving: Level 2+ and Level 3.
Thanks to a high level of integration, the R-Car V4H allows customers to develop cost-competitive, single-chip, ADAS electric control units (ECUs). These control units may support driving systems appropriate for automated driving Levels 2+ and Level 3, including full NCAP 2025 features. The R-Car V4H also supports surround view and automatic parking functions with impressive 3D visualization effects such as realistic rendering.
“We have seen excellent customer response to our R-Car V3H and V3M with high volume production, and we are pleased to extend our offering with the R-Car V4H,” said Naoki Yoshida, Vice President, Automotive Digital Products Marketing Division at Renesas. “As Renesas expands its scalable R-Car portfolio, we expect to see cutting-edge ADAS adopted in all vehicle types, from mid-range to entry-level.”

Winning Combo Solution Supports the Industry’s Stringent ASIL Requirements​

Regarding ISO 26262 functional safety, the SoC development process targets ASIL D systematic capability for all safety relevant IP. The signal processing portion of the R-Car V4H is expected to achieve ASIL B and D metrics for the real time domain.
Furthermore, Renesas provides a dedicated power solution for R-Car V4H based around the RAA271041 pre-regulator and the RAA271005 PMIC. This enables a highly reliable power supply for the R-Car V4H and peripheral memories from the 12V supply of the vehicle battery. These features enable low power operation while targeting ASIL D compliance for systematic and random hardware faults at very low BOM cost. This helps to minimize the effort of hardware and software development while reducing design complexity, cost, and time to market.

Embedded Software Platform Development Paving the Way to the Software-Defined Car​

An R-Car V4H software development kit (SDK) is also available to perform faster and easier initial device evaluation, and software development including deep learning. The SDK offers full functionality for machine learning development, and optimization of embedded systems for performance, power efficiency, and functional safety. Complete simulation models are available, and the Renesas operating system agnostic software platform enables easier development of the software-defined car.
In case of development from scratch, Fixstars’ Genesis platform enables engineers to evaluate R-Car from anywhere via their cloud solution and can provide quick and easy CNN benchmark results.

Key Features of R-Car V4H​

  • Four Arm® Cortex®-A76 at 1.8 Ghz for a total of 49KDMIPS of general compute for ADAS / AD applications
  • Three lockstep Arm® Cortex®-R52 cores at 1.4 Ghz, for a total of 9KDMIPS to support ASIL D real-time operation and eliminate the need for external microcontrollers
  • Dedicated Deep Learning & Computer Vision I/Ps with overall performance of 34 TOPS
  • Image Signal Processor (ISP) with parallel processing for machine and human vision
  • Image renderer (IMR) for fisheye distortion correction or other mathematical operation
  • Graphic processor Unit (GPU) AXM-8-256 @ 600MHz, for a total of over 150 GFLOPS
  • Dedicated automotive Interfaces: CAN, Ethernet AVB, TSN and FlexRay
  • Two fourth generation PCIe interfaces

Availability​

Samples of the R-Car V4H SoC are available now, with mass production scheduled for the second quarter of 2024. More information is available at renesas.com/r-car-V4H.
 
  • Like
  • Fire
Reactions: 16 users
Is Akida part of this?


Renesas Unveils R-Car V4H for Automated Driving Level 2+ / Level 3 to Support High-Volume Vehicle Production in 2024​


New Platform Innovates by Providing a Cutting-Edge Development Environment, Paving the Way to the Software-Defined Car
March 8, 2022
Renesas R-Car V4H SoC for Automated Driving Development of Level 2+ / Level 3
TOKYO, Japan ― Renesas Electronics Corporation (TSE:6723), a premier supplier of advanced semiconductor solutions, today announced the R-Car V4H system on chip (SoC) for central processing in advanced driver-assistance (ADAS) and automated driving (AD) solutions. The R-Car V4H achieves deep learning performance of up to 34 TOPS (Tera Operations Per Second), enabling high-speed image recognition and processing of surrounding objects by automotive cameras, radar, and lidar.
The R-Car V4H enables market-leading performance per watt through a careful combination of best-in-class IP and expert HW optimization. It targets the highest volume zones of automated driving: Level 2+ and Level 3.
Thanks to a high level of integration, the R-Car V4H allows customers to develop cost-competitive, single-chip, ADAS electric control units (ECUs). These control units may support driving systems appropriate for automated driving Levels 2+ and Level 3, including full NCAP 2025 features. The R-Car V4H also supports surround view and automatic parking functions with impressive 3D visualization effects such as realistic rendering.
“We have seen excellent customer response to our R-Car V3H and V3M with high volume production, and we are pleased to extend our offering with the R-Car V4H,” said Naoki Yoshida, Vice President, Automotive Digital Products Marketing Division at Renesas. “As Renesas expands its scalable R-Car portfolio, we expect to see cutting-edge ADAS adopted in all vehicle types, from mid-range to entry-level.”

Winning Combo Solution Supports the Industry’s Stringent ASIL Requirements​

Regarding ISO 26262 functional safety, the SoC development process targets ASIL D systematic capability for all safety relevant IP. The signal processing portion of the R-Car V4H is expected to achieve ASIL B and D metrics for the real time domain.
Furthermore, Renesas provides a dedicated power solution for R-Car V4H based around the RAA271041 pre-regulator and the RAA271005 PMIC. This enables a highly reliable power supply for the R-Car V4H and peripheral memories from the 12V supply of the vehicle battery. These features enable low power operation while targeting ASIL D compliance for systematic and random hardware faults at very low BOM cost. This helps to minimize the effort of hardware and software development while reducing design complexity, cost, and time to market.

Embedded Software Platform Development Paving the Way to the Software-Defined Car​

An R-Car V4H software development kit (SDK) is also available to perform faster and easier initial device evaluation, and software development including deep learning. The SDK offers full functionality for machine learning development, and optimization of embedded systems for performance, power efficiency, and functional safety. Complete simulation models are available, and the Renesas operating system agnostic software platform enables easier development of the software-defined car.
In case of development from scratch, Fixstars’ Genesis platform enables engineers to evaluate R-Car from anywhere via their cloud solution and can provide quick and easy CNN benchmark results.

Key Features of R-Car V4H​

  • Four Arm® Cortex®-A76 at 1.8 Ghz for a total of 49KDMIPS of general compute for ADAS / AD applications
  • Three lockstep Arm® Cortex®-R52 cores at 1.4 Ghz, for a total of 9KDMIPS to support ASIL D real-time operation and eliminate the need for external microcontrollers
  • Dedicated Deep Learning & Computer Vision I/Ps with overall performance of 34 TOPS
  • Image Signal Processor (ISP) with parallel processing for machine and human vision
  • Image renderer (IMR) for fisheye distortion correction or other mathematical operation
  • Graphic processor Unit (GPU) AXM-8-256 @ 600MHz, for a total of over 150 GFLOPS
  • Dedicated automotive Interfaces: CAN, Ethernet AVB, TSN and FlexRay
  • Two fourth generation PCIe interfaces

Availability​

Samples of the R-Car V4H SoC are available now, with mass production scheduled for the second quarter of 2024. More information is available at renesas.com/r-car-V4H.
If not, it’s getting pretty close
 
  • Like
  • Fire
Reactions: 7 users

Esq.111

Fascinatingly Intuitive.
  • Like
  • Haha
Reactions: 8 users
Morning Slade,

Thankyou for posting this article.

Regards,
Esq.

904.5 bottles of beer on the wall.........
Need to have this sung in two parts because as we know Renesas is releasing an MCU this year with AKIDA IP on board unless we do not believe the statements by for example the Acting CEO Peter van der Made.

If Renesas builds 1 million MCU's which is a conservative number and a small production run they will owe Brainchip 1 million times the royalty fee.

My opinion only DYOR
FF

AKIDA BALLISTA
 
  • Like
  • Fire
  • Wow
Reactions: 20 users
Please excuse my ignorance Tech but what is an ( R ) neural network " on chip ". Haven't as yet come across this before ?

I'm from the " old school " of computer thinking :cool::unsure::whistle:

I hope it's not a " spanner in the works " so to speak, ( if you get my drift )

I'm a retired computer engineer, and i can't get my head around this AI palaver, properly, yet, " but " as they say,

"learning all the time " ;)



Akida Ballista

hotty
Hi hotty4040
It appears that no one is going to answer your question. Well the reality is that no one can in fact answer your question yet because the terminology used in this space has not yet achieved stability. I am not a tech expert and never will be but I can research and despite all of my research and requests over at the other place a single definition of RNN does not exist. So what I commend to you is the following link which takes you to the Vorago approved Phase 1 application to NASA to harden the AKD1000 chip for space missions. If you open and read this link you will see that they refer to AKD1000 as a CNNRNN chip. I personally prefer the term SCNN - spiking convolutional neural network however if you try to find a definition of what is an SCNN it is even wider and less defined than the term RNN.

So my suggestion to you is if one of Brainchip's customers is using the term CNNRNN until proven conclusively that it is not AKD1000 keep an open mind because those who suggest otherwise would say on the basis of Vorago seeking Phase 1 approval to harden a CNNRNN chip for space missions that it definitely could not be AKD1000 but here is the proof that they would be entirely wrong:


My opinion only DYOR
FF

AKIDA BALLISTA
 
  • Like
  • Fire
Reactions: 8 users

Labsy

Regular

Renesas Automotive Semiconductors Selected by Honda for ADAS

Renesas R-Car SoC and RH850 MCU to be Used in Honda SENSING System
(Graphic: Business Wire)
(Graphic: Business Wire)
March 03, 2022 08:00 AM Eastern Standard Time
TOKYO--(BUSINESS WIRE)--Renesas Electronics Corporation (TSE:6723), a premier supplier of advanced semiconductor solutions, today announced the expansion of its collaboration with Honda in the field of advanced driver-assistance systems (ADAS).

Honda adopted Renesas’ R-Car automotive system on a chip (SoC) and RH850 automotive MCU for its Honda SENSING Elite system featured in the Legend, which went on sale in March 2021. Honda SENSING Elite incorporates advanced technology that qualifies for Level 3 automated driving (conditional automated driving in limited areas). Now Honda has again selected R-Car and RH850 for use in the Honda SENSING 360 omnidirectional safety and driver assistance system, which builds on the knowledge and expertise gained through research and development work on the earlier technology. The first automobile model equipped with Honda SENSING 360 is scheduled for release in China in 2022, with adoption in a broader range of models to follow.
Furthermore, for the next-generation Honda SENSING 360 system, Honda has selected the R-Car S4 as the main SoC in the electronic control unit (ECU), the core of the ADAS. Through this, Renesas and Honda are expanding their collaboration in the ADAS field to improve safety technologies.
“Renesas is proud to be able to contribute to innovation in Honda’s advanced safety technologies,” said Takeshi Kataoka, Senior Vice President and General Manager of the Automotive Solution Business Unit at Renesas. “Renesas shares with Honda a design philosophy that emphasizes safety and reliability above all, and we plan to further expand our collaboration to bring sophisticated driver-assistance systems to all mass-production models in the near future.”
“Honda is a global innovator in research and development work on safety technologies aimed at the realization of a society with zero traffic collision fatalities,” said Yutaka Tamagawa, Operating Executive and Head, Electronic Control Development Supervisory Unit, Monozukuri Center, Automobile Operations at Honda. “Renesas’ semiconductor devices optimized for automotive applications are extremely reliable, backed by a solid system of software and support, and provide superior power efficiency. The expansion of our collaborative efforts will speed up the development of Honda SENSING and help lead its widespread adoption.”
In the Honda SENSING Elite flagship advanced technology system, the Renesas R-Car automotive SoC processes sensing data from cameras, millimeter-wave radar, and LiDAR as well as data for 3-dimensional high-definition maps and the global navigation satellite system (GNSS). The SoC also monitors the vehicle’s position and the road conditions, and computes route plans in real time. The RH850 automotive control MCU provides support for driving operations and collision avoidance by receiving signals from R-Car and performing advanced control of the accelerator, braking, and steering systems.
The application of Honda SENSING 360 is expected to expand globally, and Renesas’ R-Car is helping to enable omnidirectional safety and driver-assistance systems by 360-degree sensing with processing sensing data from cameras and millimeter-wave radar.
Moving forward, Renesas is committed to working with Honda on the development and widespread adoption of next-generation Honda SENSING systems.
About Renesas Electronics Corporation
Renesas Electronics Corporation (TSE: 6723) delivers trusted embedded design innovation with complete semiconductor solutions that enable billions of connected, intelligent devices to enhance the way people work and live. A global leader in microcontrollers, analog, power, and SoC products, Renesas provides comprehensive solutions for a broad range of automotive, industrial, Infrastructure, and IoT applications that help shape a limitless future. Learn more at renesas.com. Follow us on LinkedIn, Facebook, Twitter, YouTube and Instagram.
Screenshot_20220309-110615_Chrome.jpg
Keep forgetting how massive this deal is with Renesas.... Billions of Ip sales coming our way in next 5 yrs guys...lest we forget.
 
  • Like
  • Fire
Reactions: 20 users

HUSS

Regular
Not sure why cloud connection is required for AC remote control if Akida chip used here for voice recognition. From my experience in construction sector is that internet cloud connection is required to ensure all HVAC and electrical systems are interfaced with BMS “Building Management System” platform for running and monitoring and controling all main equipment into one platform.

 

Attachments

  • 972439E5-C8B5-4CF1-9D74-E134E76C857E.jpeg
    972439E5-C8B5-4CF1-9D74-E134E76C857E.jpeg
    1,012.5 KB · Views: 78
  • Like
Reactions: 3 users
Not sure why cloud connection is required for AC remote control if Akida chip used here for voice recognition. From my experience in construction sector is that internet cloud connection is required to ensure all HVAC and electrical systems are interfaced with BMS “Building Management System” platform for running and monitoring and controling all main equipment into one platform.

Hi Huss
I can answer the aircon question. It allows you to turn it on in advance of your return home or turn it off following the last person to leave so it does not run all day or where you are unsure what time you will get home making setting a timer difficult.
FF

AKIDA BALLISTA
 
  • Like
Reactions: 7 users

M_C

Founding Member
Presented by:

Rahul Dubey
Rahul Dubey

Rahul Dubey, Doulos Member Technical Staff, will be presenting this training webinar, which will consist of an interactive one-hour session with Q&A participation from attendees.
This webinar will examine the use of Edge AI for Industry 4.0. It will be of interest to anyone considering the use of AI technology for constrained devices.

We’ll start by presenting an Edge AI development methodology based on Cross Industry Standard Process for Data Mining (CRISP-DM). The development framework explanation includes recommendations on quality data acquisition. Next, we’ll take a look at metrics to test model performance. Instead of developing a model from scratch, we’ll explain the use of transfer learning to create custom models. As most factory AI applications are real-time and secure, AI models are hosted on constrained devices located near the equipment or work cell. We’ll also discuss AI model quantization and API's for model inference. Two hypothetical edge AI based factory applications, predictive maintenance of machinery and work cell monitoring, are used in the webinar.

We’ll conclude with a brief explanation of how Edge AI is deployed to Industrial computers on factory floors or installed on remotely located edge devices, such as the RZ Family of MPUs from Renesas.​
Date: Wednesday, February 23, 2022
Time: 10-11am (GMT) 11am-12pm (CET) 3:30‑4:30pm (IST)
Cost: Free​
FooterImage1
 
  • Like
Reactions: 7 users

M_C

Founding Member
Well worth a listen / read


BRIAN SANTO: Nice. When you’re talking about pulling in sensor data and processing it, one approach is to push artificial intelligence out to the edge. Is that a separate trend? Or is it complementary to what we’ve just been discussing?

SAILESH CHITTIPEDDI: I certainly think it’ll be complementary to what we’re discussing. If you’re looking for defects in a line or something of that sort, that’s a perfect example of where you’d want to have as much of the AI localized as possible. If it’s a defect that’s recurring, that you see ever so often, it’s a lot simpler for it to come here, as opposed to go somewhere to the cloud, and then get it processed to stop the machine. Or to stop the process flow. So you would see a lot more of those kinds of activities happening in the future, where localized actions will drive certain sets of behaviors.

Even when it comes to things like facial recognition in an environment. One could have a separate discussion of the privacy aspects of that. But you could really have a scenario where you could identify a certain person that you don’t want entering your office environment or something like that. So those are some of the things where AI certainly is moving its way into the endpoint of the edge, if you will, of the network.

And increasingly, the one thing that’s interesting, Brian, is no single company is going to be able to address the myriad of applications in the industrial environment all by itself. So you need ecosystem partners, you need the libraries, you need the software support, to really enable your customers to come on board with a lot of these solutions into the marketplace. biometric recognition at the airport. So you could walk onto a plane without having a boarding pass or anything like that. All these are things that people are working on.
 
  • Like
Reactions: 10 users
D

Deleted member 118

Guest
  • Like
Reactions: 1 users
Top Bottom